UNIVERSITY OF MUMBAI 

INSTITUTE OF DISTANCE AND OPEN LEARNING (IDOL) 
 

 
 
STUDY MATERIAL 
 
 
 
M.A. Education, Part‐I 
Paper III : Research Methodology in Education 
 
 
 
 
 
 
 
 
 
 Syllabus 

M.A. Education, Part‐I 

Paper III : Research Methodology in Education 
 

Course Objectives: 

• To  develop  an  understanding  about  the  meaning  of  research  and  its  application  in  the  field  of 
education. 
• To enable students to prepare a research proposal. 
• To  enable  students  to  understand  different  types  of  variables,  meaning  and  types  of  hypothesis, 
sampling techniques and tools and techniques of educational research. 
• To  develop  an  understanding  about  the  different  types  of  research  methodology  of  educational 
research. 
• To enable students to understand quantitative and qualitative data analysis techniques. 
 

Module I: Educational Research and Its Design 
 

1. Educational Research : 
(a) Sources of Acquiring Knowledge: Learned authority, tradition, experience, scientific method. 
(b) Meaning, steps and scope of educational research. 
(c) Meaning,  steps  and  assumptions  of  scientific  method.   Aims and characteristics  of research as  a 
scientific activity. 
(d) Ethical Considerations in Educational Research. 
(e) Paradigms of educational research: Quantitative and Qualitative. 
(f) Types of research Fundamental, Applied and Action. 
 

2.  Research Design 

  (a) Meaning, definition, purposes and components of research design. 
  (b) Difference between the terms research method and research methodology. 
  (c)  Research Proposal : Its Meaning and Need. 
    i)  Identification of a research topic : Sources and Need 
    ii)  Review of related literature 
    iii)  Rationale and need of the study 
    iv)  Definition of the terms : Real, nominal and Operational. 
    v)  Variables. 
    vi)  Research questions, aims, objectives and hypotheses, 
    vii)  Assumptions, if any. 
    viii)  Methodology, sample and tools. 
    ix)  Scope, limitations and delimitations. 
    x)  Significance of the study. 
    xi)  Techniques of data analysis and unit of data analysis. 
    xii)  Bibliography. 
    xiii)  Time Frame. 
    xiv)  Budget, if any. 
    xv)  Chapterisation. 
 
Module II: Research Hypotheses and Sampling  
 
3.  Variables and Hypotheses 
  (a) Variables : 
    i)  Meaning of Variables 
    ii)  Types of Variables (Independent, Dependent, Extraneous, Intervening and Moderator) 
  (b) Hypotheses : 
    i)  Concept of Hypothesis  
    ii)  Sources of Hypothesis  
    iii)  Types  of  Hypothesis  (Research,  Directional,  Non‐directional,  Null,  Statistical  and  Question‐
form) 
    iv)  Formulating Hypothesis 
    v)  Characteristics of a good hypothesis 
    vi)  Hypothesis Testing and Theory  
    vii)  Errors in Testing of Hypothesis 
 
4.  Sampling : 
  (a) Concepts of Universe and Sample 
  (b) Need for Sampling 
  (c)  Characteristics of a good Sample 
  (d) Techniques of Sampling 
    i)  Probability Sampling 
    ii)  Non‐Probability Sampling 
 

 
Module III: Research Methodology, Tools and Techniques  

5.  Research Methodology  

  (a) Descriptive Research  

    i)  Causal – Comparative  

    ii)  Correlational 

    iii)  Case Study 

    iv)  Ethnography 

    v)  Document Analysis 

    vi)  Analytical Method 

  (b) Historical  Research  :  Meaning,  Scope  of  historical  research,  Uses  of  history,  Steps  of  doing 
historical  research  (Defining  the  research  problem  and  types  of  historical  inquiry,  searching  for 
historical  sources,  Summarizing  and  evaluating  historical  sources  and  Presenting  pertinent  facts 
within  an  interpretive  framework.)  Types  of  historical  sources,  External  and  internal  criticism  of 
historical sources. 

  (c)  Experimental Research  

    i)  Pre‐Experimental Design, Quasi – Experiemental Design and True – Experimental Designs,  

    ii)  Factorial Design / Independent Groups and repeated measures. 

    iii)  Nesting Design 

    iv)  Single – subject Design 

    v)  Internal and External Experimental Validity 

    vi)  Controlling extraneous and intervening variables. 
 

6.  Tools and Techniques of Research 

  (a) Classical Test Theory and Item Response Theory of Test Construction. 

  (b) Steps of preparing a research tool. 

    i)  Validity (Meaning, types, indices and factors affecting validity) 

    ii)  Reliability (Meaning, types, indices and factors affecting reliability) 

    iii)  Item Analysis (Discrimination Index, Difficulty index) 

    iv)  Index of Measurement Efficiency 

    v)  Standardisation of a tool. 
 

(c)  Tools of Research 

    i)  Rating Scale, 

    ii)  Attitude Scale, 

    iii)  Opinionnaire 

    iv)  Questionnaire 

    v)  Aptitude Test 

    vi)  Check List 

    vii)  Inventory 

    viii)  Semantic Differential Scale 

  (d) Techniques of Research 

    i)  Observation 

    ii)  Interview  

      (Tools to be used for collecting data using these techniques to be discussed in detail.) 

Module IV: Data Analysis and Report Writing 

7.  Data Analysis 

  (a) Types of Measurement Scale (Nominal, Ordinal, Interval and Ratio) 

  (b) Quantitative Data Analysis 

    i)  Parametric Techniques 

    ii)  Non‐Parametric Techniques 

    iii)  Conditions to be satisfied for using parametric techniques 

    iv)  Descriptive  data  analysis  (Measures  of  central  tendency,  variability,  fiduciary  limits  and 
graphical presentation of data) 

    v)  Inferential data analysis 

    vi)  Use of Excel in Data Analysis 
    vii)  Concepts, use and interpretation of following statistical techniques : Correlation, t‐test, z‐test, 
ANOVA,  Critical  ratio  for  comparison  of  percentages  and  chi‐square  (Equal  probability  and 
Normal Probability Hypothesis). 

    viii)  Testing of Hypothesis 

   

     (c)  Qualitative Data Analysis 

    i)  Data Reduction and Classification 

    ii)  Analytical Induction 

    iii)  Constant Comparison  

 
 

8.  Research Reporting  

  (a) Formal, Style and Mechanics of Report Writing with Reference to  

    i)  Dissertation and Thesis and 

    ii)  Paper 

  (b) Bibliography 

  (c)  Evaluation of Research Report 

References: 

1.  Best, J.W. and Kahn, J (1997) Research in Education (7th Ed) New Delhi: Prentice‐Hall of India Ltd. 

2.  Borg. B.L. (2004) Qualitative Research Methods. Boston: Pearson. 

3.  Bogdan, R.C. and Biklen, S.K. (1998) Qualitative Research for Education: An Introduction to Theory 
and Methods. Boston MA: Allyn and Bacon. 

4.  Bryman, A. (1988) Quantity and Quality in Social Science Research. London: Routledge. 

5.  Charles,  C.M.  and  Merton,  C.A.(2002)  Introduction  to  Educational  Research.  Boston:  Allyn  and 
Bacon. 

6.  Cohen, L and Manion, L. (1994) Research Methods in Education. London: Routledge. 

7.  Creswell, J.W. (2002) Educational Research. New Jersey: Upper Saddle River. 

8.  Creswell, J.W. (1994) Research Design. London: Sage Publications. 
9.  Denzine,  N.K.  and  Lincoln,  Y.S.(Eds)  (1994)  Handbook  of  Qualitative  Research  London,  Sage 
Publications. 

10.  Diener, E. and Crandall, R. (1978) Ethics in Social and Behavioural Research. Chicago: University of 
Chicago Press. 

11.  Dillon,  W.R.  and  Goldstein,  M.  (1984)  Multivariate  Analysis  Methods  and  Applications.  New  York, 
John Wiley and Sons. 

12.  Gay, L.R. and Airasian, P. (2003) Educational Research. New Jersey: Upper Saddle River. 

13.  Husen, T. and Postlethwaite, T.N. (eds.) (1994) The International Encyclopaedia of Education. New 
York: Elsevier Science Ltd. 

14.  Keeves  J.P.  (ed.)  (1988)  Educational  Research,  Methodology  and  Measurement:  An  International 
Handbook Oxford, Pergamon. 

15.  McMillan, J.H. and Schumacher, S. (2001) Research In Education. New York: Longman.  

 
 

1
EDUCATIONAL RESEARCH

Unit Structure

1.0 Objectives
1.1 Introduction
1.2 Sources Acquiring Knowledge
1.3 Meaning, Steps and Scope of Educational Research
1.4 Scientific Method, aims and characteristics of research as a scientific activity
1.5 Ethical considerations in Educational Research
1.6 Paradigms of Educational research
1.7 Types of Research
1.7.a Fundamental
1.7.b Applied Research
1.7.c. Action Research

1.0 OBJECTIVES :

After reading this unit, you will be able to:

• To explain the concept of Educational Research

• To describe the scope of Educational Research
• To state the purpose of Educational Research
• To explain what is scientific enquiry.
• To explain importance of theory development.
• To explain relationship among science, education and educational research.
• To Identity fundamental research
• To Identity applied research
• To Identify action research
• To Differentiate between fundamental, applied, and action research
• To Identify different paradigms of research
1.1 INTRODUCTION :

Research purifies human life. It improves its quality. It is search for knowledge. If shows how to
Solve any problem scientifically. It is a careful enquiry through search for any kind of Knowledge. It is a
journey from known to unknown. It is a systematic effort to gain new knowledge in any kind of
discipline. When it Seeks a solution of any educational problem it leads to educational research.
 Curiosity, inquisitiveness are natural gifts secured by a man. They inspire him to quest, increase his
thirst for knowledge / truth. After trial and error, he worked systematically in the direction of the desired
goal. His adjustment and coping with situation makes him successful in his task. Thereby he learns
something’s, becomes wise and prepares his own scientific procedure while performing the same task for
second time. So is there any relationship among science, education and educational Research?

“Research is the voyage of discovery”. It is the quest for answers to unsolved problems.

Research is required in any field to come up with new theories or modify, accept, or nullify the
existing theory. From time immemorial it has been seen so many discoveries and inventions took place
through research and world has got so many new theories which help the human being to solve his
problems. Graham Bell, Thomas Edison, JC Bose, John Dewey, Skinner, Piaget Research like have given
us theories which may cause educational progress research needs expertise.

1.2 SOURCES OF ACQUIRING KNOWLEDGE :

From the time we were born and the present day, each one of us has accumulated a body of
knowledge. Curiosity, the desire to learn about one’s environment and the desire to improve one’s life
through problem-solving is natural to all human beings. For this purpose, human beings depend on several
methods / sources of acquiring knowledge as follows:

1. Learned Authority : Human beings refer to an authority such as a teacher, a parent or the boss or an
expert or consultant and seek his / her advice. Such an authority may be based on knowledge or
experience or both. For example, if a child has difficulty in learning a particular subject, he / she may
consult a teacher. Learned authority could also be a book / dictionary / encyclopaedia / journal / web-
site on internet.

2. Tradition : Human beings easily accept many of the traditions of their culture or forefathers. For
example, in matters of food, dress, communications, religion, home remedies for minor ailments, the
way a friend will react to an invitation, one relies on family traditions. On the other hand, students, in
case of admission criteria and procedures, examination patterns and procedures, methods of
maintaining discipline, co-curricular activities, acceptable manner of greeting teachers and peers rely
on school traditions. Long established customs or practices are popular sources of acquiring
knowledge. This is also known as tenacity which implies holding on to a perspective without any
consideration of alternatives.

3. Experience : Our own prior personal experiences in matters of problem-solving or understanding

educational phenomena is the most common, familiar and fundamental source of knowledge.
4. Scientific Method : In order to comprehend and accept learning acquired through these sources, we
use certain approaches which are as follows:
(a) Empiricism : It implies relying on what our senses tell us. Through a combination of hearing and
seeing we come to know the sound of a train. i.e. through these two senses, we learn to associate
specific sounds with specific objects. Our senses also enable us to compare objects / phenomena /
events. They provide us with the means for studying and understanding relationships between
various concepts (eg. level of education and income).
(b) Rationalism : It includes mental reflection. it places emphasis on ideas rather than material
substances. if we see logical interconnectedness between two or more things, we accept those
things. For example, we may reason that conducive school / college environment is expected to
lead to better teacher performance.
 (c) Fideism : It implies the use of our beliefs, emotions or gut reactions including religion. We
believe in God because our parents told us though we had not sensed God, seen or heard him nor
had concluded that that his existence is logically proved.
1.3 MEANING, STEPS AND SCOPE OF EDUCATIONAL RESEARCH :

MEANING OF EDUCATIONAL RESEARCH :

Educational Research as nothing but cleansing of educational Research is nothing but cleansing of
educational process. Many experts think Educational Research as under-

According to Mouly, “Educational Research is the systematic application of scientific method for
solving for solving educational problem.”

Travers thinks, “Educational Research is the activity for developing science of behavior in
educational situations. It allows the educator to achieve his goals effectively.”

According to Whitney, “Educational Research aims at finding out solution of educational problems
by using scientific philosophical method.”

Thus, Educational Research is to solve educational problem in systematic and scientific manner, it
is to understand, explain, predict and control human behaviour.

Educational Research Characterizes as follows :

- It is highly purposeful.
- It deals with educational problems regarding students and teachers as well.
- It is precise, objective, scientific and systematic process of investigation.
- It attempts to organize data quantitatively and qualitatively to arrive at statistical inferences.
- It discovers new facts in new perspective. i. e. It generates new knowledge.
- It is based on some philosophic theory.
- It depends on the researchers ability, ingenuity and experience for its interpretation and conclusions.
- It needs interdisciplinary approach for solving educational problem.
- It demands subjective interpretation and deductive reasoning in some cases.
- It uses classrooms, schools, colleges department of education as the laboratory for conducting
researches.

STEPS OF RESEARCH :

The various steps involved in the research process can be summarised as follows ;

Step 1 : Identifying the Gap in Knowledge

The researcher, on the basis of experience and observation realises that some students in the class
do not perform well in the examination. So he / she poses an unanswered question : “Which factors are
associated with students’ academic performance?”
Step 2 : Identifying the Antecedent / Causes

On the basis of experience, observation and a review of related literature, he / she realises that
students who are either very anxious or not at all anxious do not perform well in the examination. Thus he
/ she identifies anxiety as one of the factors that could be associated with students’ academic performance.

Step 3 : Stating the Goals

The researcher now states the goals of the study :

1. To ascertain the relationship of anxiety with academic performance of students.
2. To ascertain the gender differences in the anxiety and academic performance of students.
3. To ascertain the gender difference in the relationship of anxiety with academic performance of
students.

Step 4 : Formulating Hypotheses

The researcher may state his / her hypotheses as follows:

1. There is a significant relationship between anxiety and academic performance of students.

2. There is a significant gender difference in the anxiety and academic performance of students.
3. There is a significant gender difference in the relationship of anxiety with academic performance of
students.

Step 5 : Collecting Relevant Information

The researcher uses appropriate tools and techniques to measure anxiety and academic performance
of students, selects a sample of students and collects data from them.

Step 6 : Testing the Hypotheses

He / she now uses appropriate statistical techniques to verify and test the hypotheses of the study
stated in Step 4.

Step 7 : Interpreting the Findings

He / she interprets the findings in terms of whether the relationship between anxiety and academic
performance is positive or negative, linear or curvilinear. He / she finds that this relationship is curvilinear
i.e. when a student’s anxiety is either very low or very high, his / her academic performance is found to be
low. But when a student’s anxiety is moderate, his / her academic performance is found to be high.

He / she now tries to explain this finding based on logic and creativity.

Step 8 : Comparing the Findings with Prior researchers’ Findings

At this step, the researcher tries to find out whether his / her conclusions match those of the prior
researches or not. If not, then the researcher attempts to find out why conclusions do not match with other
researches by analysing prior studies further.
Step 9 : Modifying Theory

On the basis of steps 7 and 8, the researcher speculates that anxiety alone cannot influence
academic performance of students. There could be a third factor which influences the relationship between
anxiety and academic performance of students. This third factor could be study habits of students. For
instance, students who have very low level of anxiety may have neglected their studies through out the
year and hence their academic performance is poor. On the other hand, students who have very high level
of anxiety may not be able to remember what they have learnt or cannot concentrate on studies due to
stress or may fall sick very often and hence cannot study properly. Hence their academic performance is
poor. However, students with a moderate level of anxiety are motivated enough to study regularly and
systematically all through the year and hence their academic performance is high.

Thus, the loosely structured theory on students’ academic performance needs to incorporate one
more variable, namely, study habits of students. In other words, it needs to be modified.

Step 10 : Asking New Questions

Do study habits and anxiety interact with each other and influence academic performance of
students? i.e. we can now start with a fresh topic of research involving three variables rather than two.

Check your Progress (1)

1. What is the aim of Educational Research?

2. Name the method which is mainly applicable in Educational Research?

3. W hich approach is adopted in Educational Research?

4. Name the places which can act as lab oratory for conducting Education Research..

SCOPE OF EDUCATIONAL RESEARCH :

Name of Educational Research changes with the gradual development occurs with respect to
knowledge and technology, so Educational Research needs to extend its horizon. Being scientific study of
educational process, it involves :

- individuals (Student, teachers, educational managers, parents.)

- institutions (Schools, colleges, research – institutes)

It discovers facts and relationship in order to make educational process more effective. It relates
social sciences like education.

It includes process like investigation, planning (design) collecting data, processing of data, their
analysis, interpretation and drawing inferences.

It covers areas from formal education and conformal education as well.

Check your Progress

1. Name disciplines on which education depends.

2. How education is an art?

3. How education is a science?

4. Name the areas of Educational Research in addition to formal education?

5. Name the aspects in which Educational Research can seek improvement?

6. Name the human elements involved in Educational Research?

7. Name the institutions involved in Educational Research?

8. Name the essential qualities of Educational Researches.

9. What is the goal of Educational Research with respect to new knowledge?

LET US SUM UP :

- Educational Research is systematic application of scientific method for solving educational problems,
regarding students and teachers as well.

- Results democratic education are slow and sometimes defective. So it needs Educational Research to
solve educational problems.

- Educational Research involves individuals like teachers / students and educational institutions. It
covers areas from formal education to nonformal education.

- Educational Research solves educational problems, purifies educative process and generates new
knowledge.

UNIT END EXERCISE :

(1) What is meant by Educational Research?

(2) What is the need of Educational Research?
(3) What is its scope?
(4) State the purpose of Education Research?

Question-1

(i) to solve education problem

(ii) scientific method
(iii) interdisciplinary approach
(iv) classroom, school, college, department of education.

Question-2
(v) Philosophy, Psychology, Sociology, History, Economics.
(vi) Since it imparts knowledge
(vii) It explains working of human mind/growth, educational program
(viii) Nonformal education, educational technology.
(ix) Curriculum, textbooks, teaching methods.
(x) Teachers, Students, Educational managers, Parents.
(xi) School, college, research-institutes.
(xii) Updated knowledge, imagination, insight, scientific attitude.
(xiii) to generate new knowledge.

References / Suggested readings.

1) Best Kahn (1955), Research in Education, New Delhi, Prentice Hall of India.
2) Kaul L. (1984) Methodology of Education research, New Delhi, Vikas Publishing House.

1.4 SCIENTIFIC METHOD, AIMS AND CHARACTERISTICS OF RESEARCH AS A

SCIENTIFIC ACTIVITY :

RELATIONSHIP AMONG SCIENCE, EDUCATION AND EDUCATIONAL RESEARCH :

Science helps to find out the truth behind the phenomenon. It is an approach to gathering of
knowledge rather than mere subject matter. It has following two main functions:

- to develop a theory.

- to deduce hypothesis from that theory.

Scientist uses an empirical approach for data collection and rational approach for development of
the theory.

Research shows a way to solve life – problems scientifically. It is a reliable tool for progress of
knowledge. Being systematic and methodological, it is treated as a science. It also helps to derive the truth
behind the knowledge. It offers methods of improving quality of the process and the product as well.
Ultimately, Science and research go hand in hand to find out solution of the problem.

Since Philosophy offers a sound basis to education, Education is considered as an art. However,
Scientific progress makes education inclining towards a science rather than an art.

Science belongs to precision and exactness. It suffers hardly from any variable. But education as a
social science suffers from many variables, so goes away from exactness. Educational Research tries to
make educative process more scientific. But education is softening from multivariable, so it can’t be as
exact as physical sciences. If the study is systematically designed to achieve educational goals, it will be an
educational research. Let us summaries this discussion with Good’s thought –

“If we wish wisdom, we must expect science. If we wish in increase in wisdom, we must expect research”

Knowledge is educator’s need. Curiosity and thirst for search makes him to follow scientific way
wisely. Indirectly, he plays a role of educational researcher. Ultimately he is able to solve the educational
problem and generate new knowledge. All the three aspects. (Science, education and educational research)
have truth as a common basis, More or less, they need exactness and precision. While solving a problem.

AIMS AND CHARACTERISTICS :

An enquiry is a natural technique for a search. But when it’s used systematically and scientifically,
it takes the form of a method. So scientific enquiry is also known as Scientific Method.

Bacon’s inductive method contributes to human knowledge. It is difficult to solve many problems
either by inductive or by deductive method. So Charles Darwin seeks happy blending of inductive and
deductive method in his scientific method. In this method, initially knowledge gained from previous
knowledge, experience, reflective thinking and observation is unorganized. Later on it proceeds
inductively from part to whole and particular to general and ultimately to meaningful hypothesis.
Thereafter, it proceeds deductively from whole to part, general to particular and hypothesis to logical
conclusion.

This method is different from the methods of knowledge – generation like trial and error,
experience, authority and intuition. It is a parallel to Dewey’s reflective thinking; because the researcher
himself is engrossed in reflective thinking while conducting research.

Scientific method follows five steps as under :

Identification and definition of the problem: The researcher states the identified problem in such a
manner that it can b solved through experimentation or observation.

Formulation of hypothesis: It allows to have an intelligent guess for the solution of the problem.

Implication of hypothesis through deductive reasoning : Here, the researcher deduces the implications
of suggested hypothesis, which may be true.

Collection and analysis of evidence: The researcher is expected here to test the deduced implications of
the hypothesis by collecting concerned evidence related to them through experimentation and observation.

Verification of the hypothesis: Later on the researcher verifies whether the evidence support hypothesis.
If it supports, the hypothesis is accepted, if it doesn’t the hypothesis is not accepted and later on it is
modified if it is necessary.

A peculiar feature of this method is not to prove the hypothesis as an absolute truth but to conclude
that the evidence does or doesn’t support the hypothesis.

LET US SUM UP :

- Scientific enquiry / Scientific method is happy blending of Inductive and deductive method. Initially it
proceeds from part to whole to state meaningful hypothesis. Later on it proceeds from whole to part and
hypothesis to logical conclusion.

- A theory is general explanation of phenomenon.

It can e refined and modified as factual knowledge. It is developed on the basis of results of
scientific method.

Unit End Exercise

i) What are the steps of scientific enquiry / method?

ii) Explain how scientific method relates theory development?
iii) What is theory? What are the principles to be considered while stating a theory?
iv) Explain the relationship among Science, Education and Educational Research?

Suggested Readings / References:

1) Best – Kahn, (1995), Research in education. New Delhi, Prentice Hall of India.
2) Ebel R.L. (1969), ‘Encyclopedia of Educational Research,’ London, The Macmillan Co.
3) Kaul L. (1984), ‘Methodology of Educational Research,’ New Delhi, Vikas Publishing House.

1.5 ETHICAL CONSIDERATIONS OF RESEARCH :

Research exerts a significant influence over educational systems. Hence a researcher needs to
adhere to an ethical code of conduct. These ethical considerations are as follows :

• While a researcher may have some obligations to his / her client in case of sponsored research
where the sponsoring agency has given him / her financial aid for conducting the research, he / she
has obligations to the users, the larger society, the subjects (sample / respondents) and professional
colleagues. He / she should not discard data that can lead to unfavourable conclusions and
interpretations for the sponsoring agency.
• The researcher should maintain strict confidentiality about the information obtained from the
respondents. No information about the personal details of the respondents should be revealed in any
of the records, reports or to other individuals without the respondents’ permission.
• The researcher should not make use of hidden cameras, microphones, tape-recorders or
observers without the respondents’ permission. Similarly, private correspondence should not be used
without the concerned respondent’s permission.
• In an experimental study, when volunteers are used as subjects, the researcher should explain the
procedures completely (eg. the experiment will go on for six months) along with the risks involved
and the demands that he / she would make upon the participants of the study (such as the subjects will
be required to stay back for one hour after school hours etc.). If possible, the subjects should be
informed about the purpose of the experiment / research. While dealing with school children (minors)
or mentally challenged students, parents’ or guardians’ consent should be obtained. This phenomenon
is known as ‘informed consent’.
• The researcher should accept the fact that the subjects have the freedom to decline to participate
or to withdraw from the experiment.
• In order to ensure the subjects’ inclusion and continuation in the experiment, the researcher
should never try to make undue efforts giving favourable treatment after the experiment, more
(additional marks) in a school subject, money and so on.
• In an experimental research which may have a temporary or permanent effect on the subjects,
the researcher must take all precautions to protect the subjects from mental and physical harm, danger
and stress.
• The researcher should make his / her data available to peers for scrutiny.
• The respondents / subjects / participants should be provided with the reasons for the
experimental procedures as well as the findings of the study if they so demand.
• The researcher should give due credit to all those who have helped him / her in the research
procedure, tool construction, data collection, data analysis or preparation of the research report.
• If at all the researcher has made some promise to the participants, it must be honoured and
fulfilled.

1.6 PARADIGMS OF EDUCATIONAL RESEARCH :

The idea of social construction of rationality can be pursued by considering Kuhn’s idea of
scientific paradigm. Thomas Kuhn, himself a historian of science, contributed to a fruitful development in
the philosophy of science with his book “The Structure of Scientific Revolutions” published in 1962. It
brought into focus two streams of thinking about what could be regarded as ‘scientific’, the Aristotelian
tradition with its teleological approach and the Galilean with its causal and mechanistic approach. It
introduced the concept of ‘paradigm’ into the philosophical debate.

Definition and Meaning of Paradigm of Research :

“Paradigm” derives from the Greek verb for “exhibiting side by side”. In lexica it is given with the
translations “examples” or table of changes in form and differences in form. Thus, Paradigms are ways of
organizing information so that fundamental, abstract relationships can be clearly understood.

The idea of paradigm directs attention to science as having recognized patterns of commitments,
questions, methods, and procedures that underlie and give direction to scientific work. Kuhn focuses upon
the paradigmatic elements of research when he suggests that science has emotional and political as well as
cognitive elements. We can distinguish the underlying assumptions of a paradigm by viewing its
discourse as having different layers of abstractions. The layers exists simultaneously and are
superimposed upon one another.

The concept of paradigm provides a way to consider the divergence in vision, custom, and tradition.
It enables us to consider science as having different sets of assumptions, commitments, procedures and
theories of social affairs.

A paradigm determines the criteria according to which one selects and defines problems for inquiry
and how one approaches them theoretically and methodologically.

A paradigm could be regarded as a cultural man made object, reflecting the dominant notions about
scientific behaviour in a particular scientific community, be it national or international, and at a particular
pointing time. Paradigms determine scientific approaches and procedures which stand out as exemplary to
the new generation of scientists – as long as they do not oppose them.

A “revolution” in the world of scientific paradigms occurs when one or several researchers at a
given time encounter anomalies or differences, for instance, make observations, which in a striking way to
not fit the prevailing paradigm. Such anomalies can give rise to a crisis after which the universe under
study is perceived in an entirely new light. Previous theories and facts become subject to thorough
rethinking and revaluation.

History of Paradigms of Research :

Educational research faces a particular problem, since education, is not a well defined, unitary
discipline but a practical art. Research into educational problems is conducted by scholars with many
disciplinary affiliations. Most of them have a background in psychology or other behavioural sciences, but
quite a few of them have a humanistic background in philosophy and history. Thus, there cannot be any
prevailing paradigm or ‘normal science’ in the very multifaceted field of educational research. However,
when empirical research conducted by behavioural scientists, particularly in the Anglo-Saxon countries, in
the 1960’s and early 1970’s began to be accused of dominating research with a positivist quantitatively
oriented paradigm that prevented other paradigms of a humanistic or dialectical nature being employed,
the accusations were directed at those with a behavioural science background.

During twentieth century two main paradigms were employed in researching educational problems.
The one is modeled on the natural sciences with an emphasis on empirical quantifiable observations which
lend themselves to analyses by means of mathematical tools. The task of research is to establish causal
relationships, to explain. The other paradigm is derived from the humanities with an emphasis on holistic
and qualitative information and interpretive approaches.

The two paradigms in educational research developed historically as follows. By the mid-nineteenth
century, when August come \91798-1857) developed positivism in sociology and John Stuart Mill (1806-
1873) empiricism in psychology. They came to serve as models and their prevailing paradigm was taken
over by social scientists, particularly in the Anglo Saxon countries. In European Continent there was
another from German idealism and Hegelianism. The “Galilean” mechanistic conception became the
dominant one particularly with mathematical physics as the methodological ideal.

There are three strands for the other main paradigm in educational research. According to the first
strand, Wilhelm Dilthey (1833-1911) maintained that the humanities had their own logic of research and
pointed out that the difference between natural sciences and humanities was that the former tried to
explain, whereas the latter tried to understand the unique individual in his or her entire, concrete setting.

The second strand was represented by the phenomenological philosophy developed by Edmund
Husserl in Germany. It emphasized the importance of taking a widened perspective and of trying to “get to
the roots” of human activity. The third strand in he humanistic paradigm consists of the critical
philosophy, which developed with certain amount of neo-Marxism.

The paradigm determines how a problem is formulated and methodologically handled. According to
the traditional positivist conception, problems related to, for example, to classroom behviour should be
investigated primarily in terms of the individual actor, either the pupils, who might be neurotic, or the
teacher who might be ill prepared for this her job. The other conception is to formulate the problem in
terms of the larger setting, that of the school, or rather that of the society at large. By means of such
mechanisms as testing, observation and the like, one does not try to find out why the pupil or the teacher
deviates from the normal. Rather an attempt is made to study the particular individual as a goal directed
human being with particular and unique motives.

Interdependence of the Paradigms :

One can distinguish between two main paradigms in educational research planning and with
different basis of knowledge. On one hand there is functional- structural, objective – rational, goal-
directed, manipulative, hierarchical, and technocratic approach. On the other hand, there is the
interpretivist, humanistic, consensual, subjective, and collegial one.

The first approach is derived from classical positivism. The second one, more popular now, partly
derived from the critical theory of the Frankfurt school, particularly from Habermas’s theory of
communicative action. The first approach is “linear” and consists of a straight forward rational action
toward preconceived problem. The second approach leaves room for reinterpretation and reshaping of the
problem during the process of dialogue prior to action and even during action.

Keeves (1988) argues that the various research paradigms employed in education, the empirical-
positivist, the hermeneutic or phenomenological, and the ethnographic-anthropological are complementary
to each other. He talks about the “unity of educational research,” makes a distinction between paradigms
and approaches, and contends that there is, in the final analysis, only one paradigm but many approaches.

For example, the teaching-learning process can be observed and /or video recorded. The
observations can be quantified and the data analyzed by means of advanced statistical method. Content can
be studied in the light of national traditions, and the philosophy underlying curriculum constructions. Both
the teaching-learning process and its outcomes can be studied in a comparative, cross-national perspective.

Depending upon the objective of a particular research project, emphasis is laid more on the one or
on the error paradigm. Thus qualitative and quantitative paradigms are more often than not
complementing each other. For example, it is not possible to arrive at any valid information about a
school or national system concerning the level of competence achieved in, for instance, science by visiting
a number of classrooms and thereby trying to collect impressions. Sample surveys like one collected by
IEA (International Association for the Evaluation of Educational Achievement) would be an important
tool. But such surveys are not much useful if it comes to accounting for factors behind the differences
between school systems. Here the qualitative information of different kinds is required.

Policymakers, planners, and administrators want generalizations and rules which apply to a wide
variety of institutions with children of rather diverse backgrounds. The policymaker and planner is more
interested in collectivity than in the individual child. They operate from the perspective of the whole
system. Whereas, the classroom practitioners are not very much helped by generalizations which apply
“on the whole” or “by and large” because they are concerned with the timely, the particular child here and
now.

Need for contemporary approaches :

The behavioural sciences have equipped educational researchers with a store of research tools, such
as observational methods and tests, which helps them to systematize observation which would otherwise
would not have been considered in the more holistic and intuitive attempts to make, for instance, informal
observations or to conduct personal interviews.

Those who turn to social science research in order to find the “best” pedagogy or the most
“efficient” methods of teaching are in a way victims of traditional science which claimed to be able to
arrive at generalizations applicable in practically every context. But, through critical philosophy
researchers have become increasingly aware that education does not take place in a social vacuum.
Educational researchers have also begun to realize that educational practices are not independent of the
cultural and social context in which they operate. Nor they are neutral to educational policies. Thus the
two main paradigms are not exclusive, but complementary to each other.

Check your progress :

Answer the following questions.

Q.1 Define the term paradigm?

Q.2 List the two paradigms of research?

LET US SUM UP :
 Fundamental Research is a basic research which is for the sake of knowledge. Applied research to
solve an immediate practical problem. Action research seeks effective way to solve a problem of the
concerned area without using a particular methodology / paradigm. Paradigm of research is way to select,
define and solve the problem methodically.

Unit End Exercise :

1. Why do we need a conduct fundamental researches?

2. In which situations can applied research be conducted?

3. How is action research different from the other types?

4. What benefits can teachers get from action research?

5. How are the paradigms dependent on each other illustrate?

References :
Thomas H. Popkewitz, Paradigms and Ideologies of Research in Education.
John W. Best and James V. Kahn (1996) Research in Education
L. R. Gay (1990) Research in Education

1.7 TYPES OF RESEARCH :

1.7.a FUNDAMENTAL RESEARCH :

It is basic approach which is for the sake of knowledge. Fundamental research is usually carried on
in a laboratory or other sterile environment, sometimes with animals. This type of research, which has no
immediate or planned application, may later result in further research of an applied nature. Basic
researches involve the development of theory. It is not concerned with practical applicability and most
closely resembles the laboratory conditions and controls usually associated with scientific research. It is
concerned establishing generally principles of learning.

For example, much basic research has been conducted with animals to determine principles of
reinforcement and their effect on learning. Like the experiment of skinner on cats gave the principle of
conditioning and reinforcement.

According to Travers, basic research is designed to add to an organized body of scientific knowledge and
does not necessarily produce results of immediate practical value. Basic research is primarily concerned with the
formulation of the theory or a contribution to the existing body of knowledge. Its major aim is to obtain and use the
empirical data to formulate, expand or evaluate theory. This type of research draws its pattern and spirit from the
physical sciences. It represents a rigorous and structured type of analysis. It employs careful sampling procedures
in order to extend the findings beyond the group or situations and thus develops theories by discovering proved
generalizations or principles. The main aim of basic research is the discovery of knowledge solely for the sake of
knowledge.

Another system for classification is sometimes used for the research dealing with these who types
of questions. This classification is based on goal or objective of the research. The first type of research,
which has its aim obtaining the empirical data that can be used to formulate, expand or evaluate theory is
called basic research. This type of study is not oriented in design or purpose towards the solution of
practical problem.

Its essential aim is to expand the frontiers of knowledge without regard to practical application. Of
course, the findings may eventually apply to practical problems that have social value.

For example, advances in the practice of medicine are dependent upon basic research in
biochemistry and microbiology. Likewise, progress in educational practices has been related to progress
in the discovery of general laws through psychological, educational, sociological research.

Check your progress – 1 :

Answer the following questions :

Q.1 What is fundamental research?

Q.2 Where can the basic researches be conducted?

1.7.b APPLIED RESEARCH :

The second type of research which aims to solve an immediate practical problem, is referred to as
applied research. According to Travers, “applied research is undertaken to solve an immediate practical
problem and the goal of adding to scientific knowledge is secondary.”

It is research performed in relation to actual problems and under the conditions in which they are
found in practice. Through applied research, educators are often able to solve their problems at the
appropriate level of complexity, that is, in the classroom teaching learning situations. We may depend
upon basic research for the discovery of more general laws of learning, but applied research much is
conducted in the order to determine how these laws operate in the classroom. This approach is essential if
scientific changes in teaching practice are to be effected. Unless educators undertake to solve their own
practical problems of this type no one else will. It should be pointed out that applied research also uses the
scientific method of enquiry. We find that there is not always a sharp line of demarcation between basic
and applied research. Certainly applications are made from theory to help in the solution of practical
problems. We attempt to apply the theories of learning in the classroom. On the other hand, basic
research may depend upon the findings of the applied research to complete its theoretical formulations. A
classroom learning experiment can throw some light on the learning theory. Furthermore, observations in
the practical situations serve to test theories and may lead to the formulation of new theories.

Most educational research studies are classified at the applied end of the continuum; they are more
concerned with “what” works best than with “why”. For example, applied research tests the principle of
reinforcement to determine their effectiveness in improving learning (e.g. programmed instruction) and
behaviour (e.g. behaviour modification). Applied research has most of the characteristics of fundamental
research, including the use of sampling techniques and the subsequent inferences about the target
population. Its purpose, however, is improving a product or a process – testing theoretical concepts in
actual problem situations. Most educational research is applied research, for it attempts to develop
generalizations about teaching – learning processes and instructional materials.

The applied research may also be employed a university or research institute or may be found in
private industry or working for a government agency. In the field of education such a person might be
employed by a curriculum publishing company, a state department of education, or a college of education
at a university. Applied researches are also found in the settings in which the application or practitioner’s
role is primary. This is where the teachers, clinical psychologists, school psychologists, social workers
physicians, civil engineers, managers, advertising specialists and so on are found. Many of theses people
receive training in doing research, and they use this knowledge for two purpose.

(1) To help practitioners understand, evaluate, and use the research produced by basic and applied
researches in their own fields and,

(2) To develop a systematic way of addressing the practical problems and questions that arise as they
practice their professions.

For example, a teacher who notices that a segment of the class is not adequately motivated in
science might look at the research literature on teaching science and then systematically try some of the
findings suggested by the research.

Some of the recent focus of applied educational research have been grading practices, collective
bargaining for school personnel, curriculum content, instructional procedures, educational technology, and
assessment of achievement. The topics have been investigated with an applied research because the
questions raised in these areas generally have limited or no concrete knowledge of theory we can draw
upon directly to aid in decision making.

Check your progress – 2 :

Answer the following questions :

Q.1 What do you mean by applied research?

Q.2 Applied research be conducted?

1.7.c ACTION RESEARCH :

Research designed to uncover effective ways of dealing with problems in the real world can be
referred to as action research. This kind of research is not confined to a particular methodology or
paradigm. For example, a study of the effectiveness of training teenage parents to care for their infants.
The study is based on statistical and other evidence that infants of teenage mothers seemed to be exposed
to more risks than other infants. The mother and children were recruited for participation in the study
while the children were still in neonate period. Mothers were trained at home or in an infant nursery. A
controlled group received no training. The mothers trained at home were visited at 2-weeks interval over a
12-month period. Those trained in nursery setting attended 3-days per week for 6 months, were paid
minimum wage, and assisted as staff in centre. Results of the study suggested that the children of both
group of trained mothers benefited more in terms of their health and cognitive measures than did the
controlled children. Generally greater benefits were realized by the children of the mothers trained in the
nursery that with the mothers trained at home.

Thus the study shows that such researches have direct application to real world problems. Second,
elements of both quantitative and qualitative approaches can be found in the study. For example,
quantitative measure of weight, height, and cognitive skills were obtained in this study. However, at the
start itself from the personal impressions and observations without the benefit of systematic quantitative
data, the researches was able to say that the mother in the nursery centre showed some unexpected
vocational aspirations to become nurses. Third, treatments and methods that are investigated are flexible
and might change during the study in response to the results as they are obtained. Thus, action research is
more systematic and empirical than some other approaches to innovation and change, but it does not lead
to careful controlled scientific experiments that are generalizable to a wide variety of situations and
settings.

The purpose of action research is to solve classroom problems through the application of scientific
methods. It is concerned with a local problem and is conducted in a local setting. It is not concerned with
whether the results are generalizable to any other setting and is not characterized by the same kind of
control evidence in other categories of research. The primary goal of action research is the solution of a
given problem, not contribution to science. Whether the research is conducted in one classroom or many
classrooms, the teacher is very much a part of the process. The more research trainings the teacher
involved have had, the more likely it is that the research will produce valid, if not generalizable research.

The value of action research is confined primarily to those who are conducting it. Despite its
shortcomings, it does represents a scientific approach to the problem solving that is considerably better
than changed based on the alleged effectiveness of untried procedures, and infinitely better than no
changes at all. It is a means by which concerned school personnel can attempt to improve the educational
process, at least within their environment. Of course, the true value of action research to true scientific
progress is limited. True progress requires the development of sound theories having implications for
many classrooms, not just one or two. One sound theory that includes ten principles of learning may
eliminate the need of hundreds of would – be action research studies. Given the current status of
educational theory, however, action research provides immediate answers to problem that can not wait for
theoretical solutions.

As John Best puts it, action research is focused on immediate applications. Its purposes is to
improve school practices and at the same time, to improve those who try to improve the practices, to
combine the research processes, habits of thinking, ability to work harmoniously with others, and
professional spirit.

If most classroom teachers are to be involved in research activity, it will probably be in the area of
action research. Many observers have projected action research nothing more than the application of
common sense or good management. Whether or not it is worthy of the term research it does not apply
scientific thinking and methods to real life problems and represents a greater improvement over teachers’
subjective judgments and decision based upon stereotype thinking and limited personal experience.

The concept of action research under the leadership of Corey has been instrumental in bringing
educational research nearer to educational practitioners. Action research is research undertaken by
practitioners in order that they may attempt to solve their local, practical problems by using the method of
science.

Check your progress – 3

Answer the following questions :

Q.1 What do you mean by action research?

Q.2 What benefits can teachers get from action research?

 
 

RESEARCH DESIGN

Unit Structure:

2.0 Objectives

2.1 (A) Meaning, definition, purpose and components of research design.

2.2 (B) Difference between the terms research method and research methodology.

2.3 (C) Research proposal: Its meaning and need

A. Identification of research topic: sources and need

B. Review of related Literature
C. Rationale and need for the study
D. Definition of Terms
E. Variables
F. Research questions, objectives and hypotheses
G. Assumptions if any
H. Scope, limitations and delimitations
I. Method, sample and tools
J. Significance of study
K. Technique for data analysis
L. Bibliography
M. Time frame
N. Budget
O. Chapterisation

2.0 OBJECTIVES :
 On completion of this unit, you will be able to :

1) State meaning of research design

2) Describe purpose of research design

3) Distinguish between research method and research methodology.

4) Discuss purposes of research proposal

5) List down various components of research proposal

6) Prepare write up for research proposal for a given topic.

2.1 (A) MEANING, DEFINITION, PURPOSE AND COMPONENTS OF RESEARCH

DESIGN

Meaning of Research Design : Before starting a research, the investigator will look for problem, he will
read books, journals, research reports and other related literature. Based on this, he will finalise the topic
for research. During this process, he will be in close contact with his guide. As soon as the topic is
decided, first task is to decide about design.

Research design is a blue print or structure with in which research is conducted. It constitutes the
blue print for the collection, measurement and analysis of data. According to Gay and Airasian (2000), “A
design is general strategy for conducting a research study. The nature of the hypothesis, the variables
involved, and the constraints of the “real world” all contribute to the selection of design.” Kothari (1988)
says, “Decisions regarding WHAT?, WHERE?, WHEN?, HOW MUCH?, by WHAT? means concerning
an inquiry or a research study constitute research design.

Thus, it can be said that research design is an outline of what the researcher will do from writing of
objectives, hypotheses and its operational implications to find analysis of data. Research design should be
able to convey following :

• What is the study about?

• Where will study be carried out?
• What type of data is necessary?
• Where necessary data is available?
• How much time is needed to complete the study?
• What will be the sampling design?
• Which tools will be identified to collect data?
• How data will be analysed?
 Depending upon the types of research the structure of design may vary. Suppose, one is conducting
an experimental research, then identification of variables, control of variables, types of experimental
design etc. be discussed properly. If someone is conducting qualitative research, then one should stress on
understanding of setting, nature of data, holistic approach, selection of participants, inductive data
analysis. Thus, according to nature and type of study the components of design will be decided.

In short, any efficient research design will help the researcher to carry out the study in a systematic
way.

PURPOSE OF RESEARCH DESIGN :

• A research design helps the investigator to obtain answers to research problem and issues involved in
the research, since it is the outline of entire research process.
• Design also tells us about how to collect data, what observation are to be carry out, how to make them,
how to analyse the data.
• Design also guides investigator about statistical techniques to be used for analysis.
• Design also guides to control certain variables in experimental research.

Thus, design guides the investigator to carry out research step by step in an efficient way. The
design section is said to be complete / adequate if investigator could carry out his research by following
the steps described in design.

2.2 (B) DIFFERENCE BETWEEN THE TERMS RESEARCH METHOD AND

RESEARCH METHODOLOGY :

While preparing the design of the study, it is necessary to think of research method. It is simply the
method for conducting research. Generally, such methods are divided into quantitative and qualitative
methods. Such quantitative methods include descriptive research, evaluation research and assessment
research. Assessment type of studies include surveys, public opinion polls, assessment of educational
achievement. Evaluation studies include school surveys, follow up studies. Descriptive research studies
are concerned with analysis of the relationships between non manipulated variables. Apart from these
quantitative methods, educational research also includes experimental and quasi experimented research,
survey research and causal-comparative research.

Qualitative research methods include ethnography, phenomenology, ethnomethodology, narrative

research, grounded theory, symbolic interaction and case study.

Thus, the researcher should mention about methods of research used in his research with proper
justification for its use.
 The term ‘methodology’ seems to be broader, in the sense it includes nature of population, selection
of sample, selection / preparation of tools, collection of data and how data will be analysed. Here the
method of research is also included.

2.3 (C) RESEARCH PROPOSAL : ITS MEANING AND NEED :

Preparing the research proposal is an important step because at this stage, entire research project
gets a concrete shape. Researcher’s insight and inspiration are translated into a step by step plan for
discovering new knowledge.

Proposal is more than research design. Research design is a subset of proposal. Ordinarily research
design will not talk much about heoretical frame work of the study. It will be also silent about the review
of related studies. A strong rationale for conducting research is also not part of research design. At the
stage of writing proposal, the entire research work shapes into concrete form. In the proposal, the
researcher demonstrates that he is familiar with what he is doing.

Following are a few purposes of a research proposal :

• The proposal is like the blue print which the architect designs before construction of a house. It
conveys the plan of entire research work along with justification of conducting the same.
• The proposal is to be presented to funding agency or a departmental research committee. Now
presentation of research proposal is compulsory before the committee as per U.G.C. guidelines of July
2009. In such a committee, a number of experts participate and suggest important points to help and
guide researcher. In fact, this is a very constructive activity. In C.A.S.E., a research proposal is
presented on three occasions. First, in the researcher’s forum on Saturday, second in Tuesday seminar
and finally before the committee consisting of Dean, Head, Guide and other experts. Such fruitful
discussion helps in resolving many issues. When such presentation is there, it always brings
seriousness on the part of researcher and guide also. During such presentation, strengths and
limitations of proposal will be come out. Funding agency also provides funds based on strength and
quality of proposal.
• Research proposal serves as a plan of action. It conveys researcher and others as to how study will be
conducted. There is indication of time schedule and budget estimates in the proposal which guides
researcher to complete the task in time with in sanctioned budget.
• The proposal approved by committee serves as a bond of agreement between researcher and guide.
Entire proposal becomes a mirror for both to execute the study further.

Thus, a research proposal serves mainly following purposes.

(i) It communicates researcher’s plan to all others interested.

(ii) It serves as a plan of action.

(iii) It is an agreement between researcher and the guide.

(iv) Its presentation before experts provide further rethinking on the entire work.

Following components are generally included in the research proposal. It is not necessary to follow
this list rigidly. It should provide useful outline for writing of any research proposal.

Normally, a research proposal begins with an Introduction, this gives clearly the background or
history of the problem selected. Some also calls this as a theoretical / conceptual framework. This will
include various theories / concepts related to problem selected. Theoretical frame work should have
logical sequence. Suppose researcher wants to study the achievement of class IX students in mathematics
in particular area, then conceptual frame may include:

• Objectives of teaching mathematics, its purpose of secondary school level

• Importance of achievement in mathematics
• Level of achievement as studied by other researchers
• Factors affecting achievements of mathematics
• Various commissions and committees views on achievement in mathematics.

All these points can be put into sequence logically. Whenever needed theoretical support be given.
This is an important step in research proposal. Generally any proposal begins with this type of
introduction.

A. Identification of Research Topic : Sources and Need :

As discussed earlier, researcher will spell out as to how the problem emerged, its social and
educational context and its importance to the field. Some researchers name this caption as background of
the study or Theoretical / Conceptual frame work of the study. In short, here the entire topic of the
research is briefly introduced along with related concepts and theories in the field.

B. Review of Related Literature :

In this section, one presents what is so far known about the problem under investigation. Generally
theoretical / conceptual frame work is already reported in earlier section. In this section researcher
concentrates on studies conducted in the area of interest. here, a researcher will locate various studies
conducted in his area and interest. Try to justify that all such located studies are ‘related ‘to your work.
For locating such studies one will refer following documents / sources.
• Surveys of research in education (Edited earlier by Prof. M. B. Buch and Later on by NCERT, New
Delhi)
• Ph. D. Theses available in various libraries.
• Current Index to Journals in Education (CIJE)
• Dissertation Abstract International (DAI)
• Educational Resources Information Centre (ERIC) by U.S. office of education.
• Various national / International journals, Internet resources (For detail see Ary, D., Jacobs, L.C., and
Razavih A. (1972). Introduction to Research in Education N. Y. Holt, Rinehart and Winston, ING pp
55 – 70)

In research proposal, the review of studies conducted earlier is reported briefly. There are two was
of reporting the same. One way could be all such related studies be reported chronologically in brief
indicating purpose, sample, tools and major findings. Of course, this will increase the volume of research
proposal. Second studies with similar trends be put together and its important trend/s be highlighted. This
is bit difficult, but innovative. Normally in review the surname of author and year in bracket is mentioned.
There is also a trend to report studies conducted in other countries separately. It is left to guide and
researcher whether such separate caption is necessary or not.

At the end of review, in research proposal, there should be conclusion. (Of course a separate
caption like conclusion be avoided.)

Here, the researcher shares the insights he has gained from the review. Also, on the basis of review
he will justice the need of conducting present study. The researcher should conclude with following points
:

• What has been done so far in this area?

• Where? (Area wise)
• When? (Year wise)
• How? (Methodology wise)
• What needs to be done?

Thus, the researcher will identify the ‘Research Gap’.

C. Rationale and Need of the Study :

Rationale should answer the question – ‘why’ this study is conducted? It ‘why’ is answered
properly, then rationale a strong one. For strong rationale, the earlier section of review will be of much
help. Identified research gaps will convey as to why this study is conducted. Suppose the investigator
wants to study the following problem : ‘Development and Try out of CAI in Teaching of Science for Class
VIII in Mumbai”.
 Here, the researcher should try to answer why CAI only? Why it is in Science teaching only? Why
it is for class VIII only? Why it is in Mumbai only?

If these questions are answered adequately, then rationale becomes strong. Here one has to identify
gaps in the area of Science teaching especially with reference to CAI. Apart from this, the need for
conducting the present study be justified.

D. Definition of Terms :

Every research study involves certain key or technical terms which have some special connotation
in the context of study; hence it is always desirable to define such key words. There are two types
definitions, (i) Theoretical / constitutive and (ii) Operational.

A constitutive definition elucidates a term and perhaps gives some more insight into the phenomena
described by the terms. Thus, this definition is based on some theory. While an operational definition is
one which ascribes meaning to a concept by specifying the operations that must be performed in order to
measure the concept, e.g. the word ‘achievement’ has many meanings but operationally it can be defined
as, “the scores obtained by the students in English test constructed by researcher in 2009. Here it is clear
that achievement in English will be measured by administering to test constructed by Mr. So and So in
2009. Apart from operational definitions, one can define some terms which have definite meaning with
reference to particular investigation. The terms like Lok Jumbish, Minimum Levels of Learning,
Programmed Learning etc. can be define in particular context of research.

E. Variables :

Variables involved in the research need to be identified here. Their operational definitions should
be given in the research proposal. Especially in study where experimental research is conducted, variables
be specified with enough care. Their classification should be done in terms and dependent variables,
independent variables, intervening variables, extraneous variables etc. Controlling of some variables need
to be discussed at an appropriate stage in proposal.

F. Research questions objectives and hypotheses:

While reading the statement of the problem, there may be bit confusion to avoid such confusions
there is a need to have specification of a research problem. This specification can be done by writing
research questions, objectives, hypotheses, by writing operational definitions thus, objectives give more
clarity to researchers and reactors objectives are the foundations of the research, as they will guide the
entire process of research. List of objectives should not be too lengthy not ambiguous. The objectives we
stated clearly to indicate what the researcher is trying to investigate.

While conducting any research, researcher would definitely aim at assuring certain questions. The
researcher should frame such questions in a praise way. Some researchers simply put the objectives in the
question form, which is just duplication of objectives, which be avoided.

Depending on the nature of study, the researcher would formulate hypotheses, The proposition of a
hypothesis is derived from theoretical constructs, previous researches on earlier researches, the researcher
can write research or will hypothesis will be more suitable however as per evidences from previous
researches one can decide the nature of hypothesis.

Formulation of hypothesis is an indication that researcher has sufficient knowledge in the area and
it also gives direction for data collection and analysis. A hypothesis has to be :

(I) testable, (ii) have explanatory power, (iii) state expected relationship between variables. (iv) consistent
with existing body of knowledge.

G. Assumptions:

Best and Kahn (2004) assumptions are statements of what the researcher believes to be facts
but cannot verify. If the researcher is proceeding with certain assumptions, then same need to be reported
in the research proposal.

H. Scope, Limitations and Delimitations:

In any research, it is not possible to cover all aspects of the area of interest, variables, population
and so on. Thus, a study has always certain limitations. Limitations are those conditions beyond the control
of the researcher that may play restriction on conclusions. Sometimes, the tool used is not revalidated. This
itself becomes limitation of the study. Thus limitation is a broad term, but delimitation is a narrow term. It
indicates boundaries of the study. The study on achievement in English can be delimited to only grant-in-
aid school, which includes schools who follow Maharashtra State Board, so here beyond this conclusion
can not be extended. This can be made more specific by specifying the population and sample.

I. Method, Sample and Tools:

Method: A researcher should report about method of research. As discussed in (b), researcher should
mention as to how study will be conducted. Depending on nature of study – qualitative or quantitative the
method of research need to be reported along with justification. i.e. how particular method suits one’s
study be discussed in brief. If it is survey, do not write simply survey, but indicate further the type of
survey too. If it is experimental design, mention specifically which type of experimental design.

Sample : You might have already studied about sampling in details. This section of research proposal will
mention about selection of sample. First, the researcher should mention about would like to in for. One
must describe the population along with total size. This is especially needed in case of randomization and
stratification. Researcher should mention about probability non probability sampling design. Accordingly
selection of sample need to be detailed out along with its justification. Many researchers write about
randomization without mentioning size of population. the researcher also writes about stratified sampling
without details of various strata along with its size. As from the sample statistics, population parameter is
to be estimated, solution of sample be done with enough care.

In case of qualitative research, investigator may go for theoretical sampling. It is necessary to

derailed out have , it need be, description of field is necessary.

Tools : You have already shared about various tools of data collection. In this section of proposal selection
and description of tool is for be reported with proper justification. Steps of construction of particular tool
need to be reported in brief. If readymade tools are used then its related details need to be reported. Details
like author of the tool, its reliability, validity, and norms, along with scoring procedure need to be reported.
It has been found that many researchers fail to report the year when tool was constructed. As far as
possible, very old tools need to be avoided. In case of readymade tools, always look for which population
it was desirable to use valid and reliable tools.

J. Significance of the Study :

If we have already reported strong rationale then, hardly there is any need to go for significance. In
rationale part, one must describe as to how this study will contribute to the field of education. How the
findings / results of particular research will influence educational process in general need to be reported in
the rationale only.

(Note : There are various models for writing research proposal. It differs from university to university.
Many funding agencies have their own format for proposal.)

K. Technique/s of Data Analysis :

 This is crucial step in proposal. As to how collected data will be tabulated and organized for the
purpose of further analysis is to be reported in this section. If it is a quantitative research, parametric or
non-parametric statistical techniques will be used need to be reported. Before applying any technique for
data analysis, verify the needed assumptions about that particular technique. Suppose if one wants to go
for ANOVA, verify about assumption for normality, nature of data – especially in interval or ratio scale,
homogeneity of variances and randomization. If it is qualitative analysis, detailed out about nature of data,
its tabulation, orgnaisation and description. If data are to be analysed with the help of content analysis,
how exactly it will be done needs to be detailed out. Whichever technique one is using, it needs to be in
tune with objectives and hypotheses of study.

L. Bibliography :

During preparation of proposal, researcher consults various sources like books, journals, reports,
Ph.D. theses etc. All such primary / secondary sources need to be reported in the bibliography. Generally
American Psychological Association – Publication Manual be followed to write references. All authors
quoted in proposal need to be listed in bibliography. Authors who are not quoted but they are useful for
further reading be also listed. Consistency and uniformity be observed in reporting references.

M. Time Frame :

The proposal submitted for M.Phil or Ph.D. degrees, generally do not require time frame in all
universities, but there is a fixed limit for these courses. It is always advisable to give detailed schedule if
research work, as it helps to keep researcher alert. Proposals to be submitted to funding agency definitely
ask for time frame. Time frame need to be reported keeping following points in view. Time / duration
mentioned by funding agency be properly dividend.

• Time required for preliminary work like review of literature.

• Time required for preparing tool/s.
• Time require for data collection, field visits etc.
• Time required for data analysis and report writing.

N. Budget :

The proposal submitted to the funding agency needs details regarding financial estimates. It may
include expected expenditure keeping various budget needs. Following budget needs be kept in view
along with amount.
• Remuneration for project team, i.e. principal investigator and project team.
• Remuneration for secretarial staff like clerk, data entry operator, accountants, helpers etc.
• Remuneration for appointing project fellow, field investigators etc.
• Expenditure towards purchase of books, journals, tools etc.
• Expenditure towards printing, xeroxing, stationery etc.
• Expenditure for data entry, tabulation and analysis of data.
• Expenditure for field work, travel for monitoring purpose etc.
• Expenditure for preparing final report.

While preparing budget, examine the guidelines given by particular funding agency.

O. Chapterisation :

Generally scheme of chapterisation is given in synopsis. If at all it is to be reported in research

proposal write down various caption, sub captions in each chapter, format for thesis is given by few
universities, same be followed.

Check Your Progress – I

(a) Select one topic for research in education and write a various steps of research proposal at length.

Suggested Readings :

1) Best, J.W. and Kahn, J.V. (2004), Research in Education, New Delhi, Prentice Hall of India.

2) Gay, L.R. and Airasian, P. (2000), Educational Research : Competencies for Analysis and Application,
New Jersey : Mersil.

3) Kothari, R.C. (1985), Research Methodology, New Delhi : Wiley Eastern Ltd.
 3

VARIABLES AND HYPOTHESES 
 
Unit Structure 
 
3.0      Objectives 
3.1      Introduction 
3.2      Meaning of variables 
3.3 Types of variables (independent, dependent, Extraneous, Intervening and Moderator) 
3.4      Concept of hypothesis 
3.5      Sources of hypothesis 
3.6 Types of hypothesis (Research, Directional, Non Directional, Null, Statistical and question form 
3.7      Formulating hypothesis 
3.8      Characteristics of a good hypothesis 
3.9 Hypothesis testing and theory 
3.10 Errors in testing of hypothesis 
3.11 Summary 
 

3.0 OBJECTIVES:        
 

After reading this unit you will be able to: 

• Define variables 
• Identify the different types of variables 
• Show the relationship between the variables 
• Explain the concept of hypotheses 
• State the sources of hypotheses 
• Explain different types of hypothesis 
• Identify types of hypothesis 
 • Frame hypotheses skillfully 
• Describe the characteristics of a good hypothesis 
• Explain the significance level in hypothesis testing 
• Identify the errors in testing of hypothesis 
 

3.1  INTRODUCTION:  
 

Each person/thing we collect data on is called an observation (in our research work these are 
usually people/subjects). Observation (participants) possess a variety of characteristics. If a characteristic 
of an observation (participant) is the same for every member of the group i.e. it does not vary, it is called 
a constant. If a characteristic of an observation (participant) differs for group members it is called a 
variable. In research we do not get excited about constants (since everyone is the same on that 
characteristic); we are more interested in variables.  
 

3.2  MEANING OF VARIABLES 
 

A variable is any entity that can take on different values. So what does that mean? Anything that
can vary can be considered a variable. For instance, age can be considered a variable because age can take
different values for different people or for the same person at different times. Similarly, country can be
considered a variable because a person's country can be assigned a value.

A variable is a concept or abstract idea that can be described in measurable terms. In research,
this term refers to the measurable characteristics, qualities, traits, or attributes of a particular
individual, object, or situation being studied.

Variables are properties or characteristics of some event, object, or person that can take on different
values or amounts.

Variables are things that we measure, control, or manipulate in research. They differ in many 
respects, most notably in the role they are given in our research and in the type of measures that can 
be applied to them.  
 
By itself, the statement of the problem usually provides only general direction for the research 
study; it does not include all the specific information.  There is some basic terminology that is extremely 
important in how we communicate specific information about research problems and about research in 
general.  
 
Let us analyse an example; if a researcher is interested in the effects of two different teaching 
methods on the science achievement of fifth‐grade students, the grade level is constant, because all 
individuals involved are fifth‐graders. This characteristic is the same for everyone; it is a ‘constant’ 
condition of the study. After the different teaching methods have been implemented, the fifth‐graders 
involved would be measured with a science achievement test.  It is very unlikely that all of the fifth‐
graders would receive the same score on this test, hence the score on the science achievement test 
becomes a variable, because different individuals will have different scores; at least, not all individuals 
will have the same scores.  We would say that science achievement is a variable, but we would mean, 
specifically, that the score on the science achievement test is a variable. 
 
There is another variable in the preceding example  – the teaching method.  In contrast to the 
science achievement test score, which undoubtedly would be measured on a scale with many possible 
values, teaching method is a categorical variable consisting of only two categories, the two methods.  
Thus, we have different kinds of variables and different names or classifications for them.   
 
A concept which can take on different quantitative values is called a variable.  As such the 
concepts like weight, height, income are all examples of variables.  Qualitative phenomena (or the 
attributes) are also quantified on the basis of the presence or absence of the concerning attributes(s).    
Age is an example of continuous variable, but the number of male and female respondents is an example 
of discrete variable. 
 

3.3 TYPES OF VARIABLES:     
    
There are many classification systems given in the literature the names we use are descriptive; 
they describe the roles that variables play in a research study.  The variables described below by no 
means exhaust the different systems and names that exist, but they are the most useful for 
communicating about educational research.  
 
3.3.1 Independent variables:  
 

 Independent variables are variables which are manipulated or controlled or changed. In the 
example “a study of the effect of teacher praise on the reading achievement of second‐graders”, the 
effect of praise, the researcher is trying to determine whether there is a cause‐and‐effect relationship, so 
the kind of praise is varied to see whether it produces different scores on the reading achievement test.  
We call this a manipulated independent variable (treatment variable).  The amount and kind of praise is 
manipulated by the researcher.  The researcher could analyze the scores for boys and girls separately to 
see whether the results are the same for both genders.  In this case gender is a classifying or attributes 
independent variable. The researcher cannot manipulate gender, but can classify the children according 
to gender.  
 
3.3.2 Dependent variables:  
 

 Dependent variables are the outcome variables and are the variables for which we calculate 
statistics. The variable which changes on account of independent variable is known as dependent 
variable. 
 
 Let us take the example, a study of the effect of teacher praise on the reading achievement of 
second‐graders; the dependent variable is reading achievement.  We might compare the average reading 
achievement scores of second‐graders in different praise conditions such as no praise, oral praise, written 
praise, and combined oral and written praise.   
 
  The following example further illustrates the use of variables and constants.  In a study conducted 
to determine the effect of three different teaching methods on achievement in elementary algebra, each 
of three ninth‐grade algebra sections in the same school, taught by the same teacher, is taught using one 
of the methods.  Both boys and girls are included in the study.  The constants in the study are grade level, 
school, and teacher.  (This assumes that, except for method, the teacher can hold teaching effectiveness 
constant.)  The independent variables in the study are teaching method and gender of the student.  
Teaching method has three levels that arbitrarily can be designated methods A, B, and C; gender of the 
student, of course, has two levels.  Achievement in algebra, as measured at the end of the instructional 
period, is the dependent variable. 
 
The terms dependent and independent variable apply mostly to experimental research where 
some variables are manipulated, and in this sense they are "independent" from the initial reaction 
patterns, features, intentions, etc. of the subjects. Some other variables are expected to be "dependent" 
on the manipulation or experimental conditions. That is to say, they depend on "what the subject will do" 
in response. Somewhat contrary to the nature of this distinction, these terms are also used in studies 
where we do not literally manipulate independent variables, but only assign subjects to "experimental 
groups" based on some pre‐existing properties of the subjects. . Independent variables are those that are 
manipulated whereas dependent variables are only measured or registered. 
 
Consider other examples of independent and dependent variables: 
 
Example 1:  A study of teacher‐student classroom interaction at different levels of schooling. 
 
Independent variable:  Level of schooling, four categories – primary, upper primary, secondary and 
junior college. 
 
Dependent variable: Score on a classroom observation inventory, which measures teacher – student 
interaction 
 
Example 2: A comparative study of the professional attitudes of secondary school teachers by gender. 
 
Independent variable: Gender of the teacher – male, female. 
 
Dependent variable: Score on a professional attitude inventory. 
 
3.3.3 Extraneous variable:  
 
Independent variables that are not related to the purpose of the study, but may affect the 
dependent variable are termed as extraneous variables.  Suppose the researcher wants to test the 
hypothesis that there is a relationship between children’s gains in social studies achievement and their 
self‐concepts.   In this case self‐concept is an independent variable and social studies achievement is a 
dependent variable.  Intelligence may as well affect the social studies achievement, but since it is not 
related to the purpose of the study undertaken by the researcher, it will be termed as an extraneous 
variable.  Whatever effect is noticed on dependent variable as a result of extraneous variable(s) is 
technically described as an ‘experimental error’.  A study must always be so designed that the effect 
upon the dependent variable is attributed entirely to the independent variable(s), and not to some 
extraneous variable or variables.  
 
E.g.  Effectiveness of different methods of teaching Social Science. 
Here variables such as teacher’s competence, Teacher’s enthusiasm, age, socio economic status 
also contribute substantially to the teaching learning process. It cannot be controlled by the researcher. 
The conclusions lack incredibility because of extraneous variables. 
 
3.3.4 Intervening variables:  
 

They intervene between cause and effect. It is difficult to observe, as they are related with 
individuals feelings such as boredom, fatigue excitement At times some of these variables cannot be 
controlled or measured but have an important effect upon the result of the study as it intervenes 
between cause and effect. Though difficult, it has to be controlled through appropriate design. 
Eg. “Effect of immediate reinforcement on learning the parts of speech”. 
 
Factors other than reinforcement such as anxiety, fatigue, and motivation may be intervening 
variables. They are difficult to define in operational, observable terms however they cannot be ignored 
and must be controlled using appropriate research design. 
 
3.3.5 Moderator:  
 

A third variable that when introduced into an analysis alters or has a contingent effect on the 
relationship between an independent and a dependent variable. A moderator variable is an independent 
variable that is not of primary interest that has levels, which when combined with the levels of the 
independent variable of interest produces different effects.   
 
  For example, suppose that the researcher designs a study to determine the impact of the lengths 
of reading passages on the comprehension of the reading passage.  The design has three levels of 
passage length: 100 words, 200 words, and 300 words.  The participants in the study are fourth‐fifth‐ and 
sixth‐graders.  Suppose that the three grade levels all did very well on the 100‐word passage, but only the 
sixth‐graders did very well on the 300‐word passage.  This would mean that successfully comprehending 
reading passages of different lengths was moderated by grade level.  
 
 
 
 
Check your progress: 
1. What is a Variable?  

 
 

 
2. Identify the variables in this example “Teaching effectiveness of secondary school teachers in relation 
to their presage characteristics”.  
 

3.4 CONCEPT OF HYPOTHESIS  
 

Hypothesis is usually considered as the principal instrument in research.  The derivation of a 
suitable hypothesis goes hand in hand with the selection of a research problem. A hypothesis, as a 
tentative hunch, explains the situation under observation so as to design the study to prove or disprove 
it. What a researcher is looking for is a working or positive hypothesis. It is very difficult, laborious and 
time consuming to make adequate discriminations in the complex interplay of facts without hypothesis. 
It gives definite point and direction to the study, prevents blind search and indiscriminate gathering of 
data and helps to delimit the field of inquiry.  
 
3.4.1 Meaning: 
 
 The word hypothesis (plural is hypotheses) is derived from the Greek word – ‘hypotithenai’ 
meaning ‘to put under’ or ‘to suppose’ for a hypothesis to be put forward as a scientific hypothesis, the 
scientific method requires that one can test it. Etymologically hypothesis is made up of two words, 
“hypo” (less than) and “thesis”, which mean less than or less certain than a thesis.  It is the presumptive 
statement of a proposition or a reasonable guess, based upon the available evidence, which the 
researcher seeks to prove through his study. 
According to Lundberg, “A hypothesis is a tentative generalisation, the validity of which remains to
be tested. In its most elementary stage, the hypothesis may be any hunch, guess, imaginative idea, which
becomes the basis for action or investigation.

Goode and Hatt have defined it as “a proposition which can be put to test to determine its validity”.
A hypothesis is a statement temporarily accepted as true in the light of what is, at the time, known about a
phenomenon, and it is employed as a basis for action in the search of new truth.

A hypothesis is a tentative assumption drawn from knowledge and theory which is used as a guide 
in the investigation of other facts and theories that are yet unknown. 
 
It is a guess, supposition or tentative inference as to the existence of some fact, condition or 
relationship relative to some phenomenon which serves to explain such facts as already are known to 
exist in a given area of research and to guide the search for new truth. 
Hypotheses reflect the research worker’s guess as to the probable outcome of the experiments. 
 
A hypothesis is therefore a shrewd and intelligent guess, a supposition, inference, hunch, 
provisional statement or tentative generalization as to the existence of some fact, condition or 
relationship relative to some phenomenon which serves to explain already known facts in a given area of 
research and to guide the search for new truth on the basis of empirical evidence.  The hypothesis is put 
to test for its tenability and for determining its validity. 
 
In this connection Lundberg observes: Quite often a research hypothesis is a predictive statement, 
capable of being tested by scientific methods, that relates an independent variable to some dependent 
variable.  For example, consider statements like the following ones: “Students who receive counselling 
will show a greater increase in creativity than students not receiving counseling” or “There is a positive 
relationship between academic aptitude scores and scores on a social adjustment inventory for high 
school students” 
 
 
These are hypotheses capable of being objectively verified and tested.  Thus, we may conclude 
that a hypothesis states what we are looking for and it is a proposition which can be put to a test to 
determine its validity. 
 
3.4.2 Importance of the Hypotheses: 
 
 The importance of hypotheses is generally recognized more in the studies which aim to make 
predictions about some outcome.  In experimental research, the researchers is interested in making 
predictions about the outcome of the experiment or what the results are expected to show and 
therefore the role of hypotheses is considered to be of utmost importance. In the historical or descriptive 
research, on the other hand, the researcher is investigating the history of a city or a nation, the life of a 
man, the happening of an event, or is seeking facts to determine the status quo of some situation and 
thus may not have a basis for making a prediction of results.  A hypothesis, therefore, may not be 
required in such fact‐finding studies. Hillway (1964) too is of the view that “when fact‐finding alone is the 
aim of the study, a hypothesis may not be required.” 
 
Most historical or descriptive studies, however, involve not only fact‐finding but interpretation of 
facts to draw generalizations.  If a researcher is tracing the history of an educational institution or making 
a study about the results of a coming assembly poll, the facts or data he gathers will prove useful only if 
he is able to draw generalizations from them.  Whenever possible, a hypothesis is recommended for all 
major studies to explain observed facts, conditions or behaviour and to serve as a guide in the research 
process. The importance of hypotheses may be summarized as under. 
 
1. Hypotheses facilitate the extension of knowledge in an area.  They provide tentative explanations of 
facts  and  phenomena,  and  can  be  tested  and  validated.  It  sensitizes  the  investigator  to  certain 
aspects of situations which are relevant from the standpoint of the problem in hand.   
 
2. Hypotheses provide the researcher with rational statements, consisting of elements expressed in a 
logical order of relationships which seek to describe or to explain conditions or events, that have not 
yet been confirmed by facts.  The hypotheses enable the researcher to relate logically known facts 
to  intelligent  guesses  about  unknown  conditions.  It  is  a  guide  to  the  thinking  process  and  the 
process of discovery.  It is the investigator’s eye – a sort of guiding light in the work of darkness. 
 
3. Hypotheses provide direction to the research. It defines what is relevant and what is irrelevant. The 
hypotheses  tell  the  researcher  specifically  what  he  needs  to  do  and  find  out  in  his  study.  Thus  it 
prevents the review of irrelevant literature and the collection of useless or excess data.  Hypotheses 
provide a basis for selecting the sample and the research procedures to be used in the study. The 
statistical techniques needed in the analysis of data, and the relationships between the variables to 
be tested, are also implied by the hypotheses.  Furthermore, the hypotheses help the researcher to 
delimit his study in scope so that it does not become broad or unwieldy. 
 
4. Hypotheses provide the basis for reporting the conclusions of the study.  It serves as a framework 
for  drawing  conclusions.  The  researcher  will  find  it  very  convenient  to  test  each  hypothesis 
separately and state the conclusions that are relevant to each.  On the basis of these conclusions, he 
can make the research report interesting and meaningful to the reader. It provides the outline for 
setting conclusions in a meaningful way. 
 
Hypothesis has a very important place in research although it occupies a very small pace in the 
body of a thesis.  It is almost impossible for a research worker not to have one or more hypotheses 
before proceeding with his work.   
  

3.5  SOURCES OF HYPOTHESIS: 

 
The derivation of a good hypothesis demands characteristic of experience and creativity. Though 
hypothesis should precede the gathering of data, a good hypothesis can come only from experience.  
Some degree of data gathering, the review of related literature, or a pilot study must precede the 
development and gradual refinement of the hypothesis. A good investigator must have not only an alert 
mind capable of deriving relevant hypothesis, but also a critical mind capable of rejecting faulty 
hypothesis.   
 
 
What is the source of hypotheses?  They may be derived directly from the statement of the 
problem; they may be based on the research literature, or in some cases, such as in ethnographic 
research, they may (at least in part) be generated from data collection and analysis.  The various sources 
of hypotheses may be: 
 

♦ Review of similar studies in the area or of the studies on similar problems; 
♦ Examination of data and records, if available, concerning the problem for possible trends, peculiarities 
and other clues; 
♦ Discussions with colleagues and experts about the problem, its origin and the objectives in seeking a 
solution. 
♦ Exploratory  personal  investigation  which  involves  original  field  interviews  on  a  limited  scale  with 
interested  parties  and  individuals  with  a  view  to  secure  greater  insight  into  the  practical  aspects  of 
the problem. 
♦ Intuition is often considered a reasonable source of research hypotheses ‐‐ especially when it is the 
intuition of a well‐known researcher or theoretician who “knows what is known”  
♦ Rational  Induction  is  often  used  to  form  “new  hypotheses”  by  logically  combining  the  empirical 
findings from separate areas of research  
♦ Prior empirical research findings are perhaps the most common source of new research hypotheses, 
especially when carefully combined using rational induction  
♦ Thus  hypothesis  are  formulated  as  a  result  of  prior  thinking  about  the  subject,  examination  of  the 
available data and material including related studies and the council of experts. 
 
Check your progress: 
 
1.  Define hypothesis.  
 

 
 

 
 
2.  Hypothesis is stated in researches concerned with      

        
3.  What are the sources of hypotheses?  

3.6   TYPES OF HYPOTHESIS : 

 
3.6.1  Research hypothesis: When a prediction or a hypothesized relationship is to be tested by scientific 
methods, it is termed as research hypothesis. The research hypothesis is a predictive statement 
that relates an independent variable to a dependent variable.  Usually a research hypothesis must 
contain, at least, one independent and one dependent variable. A research hypothesis must be 
stated in a testable form for its proper evaluation. As already stressed, this form should indicate a 
relationship between the variables in clear, concise, and understandable language. Research 
hypotheses are classified as being directional or non‐directional.   
 
3.6.2 Directional hypothesis: The hypotheses which stipulate the direction of the expected differences 
or  relationships  are  terms  as  directional  hypotheses.    For  example,  the  research  hypothesis: 
“There will be a positive relationship between individual’s attitude towards high caste Hindus and 
his  socio‐economic  status,”  is  a  directional  research  hypothesis.    This  hypothesis  stipulates  that 
individuals  with  favourable  attitude  towards  high  cast  Hindus  will  generally  come  from  higher 
socio‐economic  Hindu  families  and  therefore  it  does  stipulate  the  direction  of  the  relationship.  
Similarly, the hypothesis: “Adolescent boys with high IQ will exhibit low anxiety than adolescent 
boys  with  low  IQ”  is  a  directional  research  hypothesis  because  it  stipulates  the  direction  of  the 
difference between groups.  
3.6.3 Non‐directional  hypothesis:  A  research  hypothesis  which  does  not  specify  the  direction  of 
 expected differences or relationships is a non‐directional research hypothesis.  For example, the 
hypotheses: “There will be difference in the adaptability of fathers and mothers towards rearing of 
their children” or “There is a difference in the anxiety level of adolescent girls of high IQ and low 
IQ” are non‐directional research hypotheses.  Although these hypotheses stipulate there will be a 
difference, the direction of the difference is not specified. A research hypothesis can take either 
statistical form, declarative form, the null form, or the question form. 
 
3.6.4 Statistical  hypothesis:  When  it  is  time  to  test  whether  the  data  support  or  refute  the  research 
hypothesis, it needs to be translated into a statistical hypothesis. A statistical hypothesis is given in 
statistical terms.  Technically, in the context of inferential statistics, it is a statement about one or 
more parameters that are measures of the populations under study.  Statistical hypotheses often 
are given in quantitative terms, for example: “The mean reading achievement of the population of 
third‐grade students taught by Method A equals the mean reading achievement of the population 
taught  by  Method  B.”  Therefore  we  can  say  that  statistical  hypotheses  are,  concerned  with 
populations  under  study.    We  use  inferential  statistics,  to  draw  conclusions  about  population 
values even though we have access to only a sample of participants.  In order to use inferential 
statistics,  we  need  to  translate  the  research  hypothesis  into  a  testable  form,  which  is  called  the 
null hypothesis. An alternative or declarative hypothesis indicates the situation corresponding to 
when the null hypothesis is not true.  The stated hypothesis will differ depending on whether or 
not it is a directional research hypothesis. 
 
3.6.5 Declarative hypothesis: When the researcher makes a positive statement about the outcome of the 
study, the hypothesis takes the declarative form.  For example, the hypothesis: “The academic 
achievement of extroverts is significantly higher than that of the introverts,” is stated in the 
declarative form.  In such a statement of hypothesis, the researcher makes a prediction based on 
his theoretical formulations of what should happen if the explanations of the behaviour he has 
given in his theory are correct. 
 
3.6.6 Null  hypothesis:  In  the  null  form,  the  researcher  makes  a  statement  that  no  relationship  exists. 
The  hypothesis,  “There  is  no  significant  difference  between  the  academic  achievement  of  high 
school athletes and that of non athletes,” is an example of null hypothesis.  Since null hypotheses 
can be tested statistically, they are often termed as statistical hypotheses.  They are also called the 
testing  hypotheses  when  declarative  hypotheses  are  tested  statistically  by  converting  them  into 
null form.  It states that even where it seems to hold good it is due to mere chance.  It is for the 
researcher to reject the null hypothesis by showing that the outcome mentioned in the declarative 
hypothesis does occur and the quantum of it is such that it cannot be easily dismissed as having 
occurred by chance. 
 
3.6.7 Question  form  hypothesis:  In  the  question  form  hypothesis,  a  question  is  asked  as  to  what  the 
outcome will be instead of stating what outcome is expected.  Suppose a researcher is interested 
in knowing whether programmed instruction has any relationship to test anxiety of children.   
 

• The declarative form of the hypothesis might be:  “Teaching children through the programmed 
instruction material will decrease their test anxiety”.   
 
 • The null form would be: “teaching children through programmed instruction material will have 
no  effect  on  their  test  anxiety.’  This  statement  shows  that  no  relationship  exists  between 
programmed instruction and test anxiety.   
 

• The  question  form  puts  the  statement  in  the  form:  “Will  teaching  children  through 
programmed instruction decrease their test anxiety?”  
 

3.7   FORMULATING HYPOTHESIS: 
 

Hypotheses are guesses or tentative generalizations, but these guesses are not merely accidents. 
Collection of factual information alone does not lead to successful formulation of hypotheses. 
Hypotheses are the products of considerable speculation and imaginative guess work.  They are based 
partly on known facts and explanations, and partly conceptual.  There are no precise rules for formulating 
hypotheses and deducing consequences from them that can be empirically verified.  However, there are 
certain necessary conditions that are conducive to their formulation.  Some of them are: 
 

• Richness  of  background  knowledge.    A  researcher  may  deduce  hypotheses  inductively  after  making 
observations  of  behaviour,  noticing  trends  or  probable  relationships.    For  example,  a  classroom 
teacher  daily  observes  student  behaviour.    On  the  basis  of  his  experience  and  his  knowledge  of 
behaviour in a school situation, the teacher may attempt to relate the behaviour of students to his 
own, to his teaching methods, to changes in the school environment, and so on.  From these observed 
relationships,  the  teacher  may  inductively  formulate  a  hypothesis  that  attempts  to  explain  such 
relationships. 
 
Background knowledge, however, is essential for perceiving relationships among the variables 
and to determine what findings other researchers have reported on the problem under study.  New 
knowledge, new discoveries, and new inventions should always form continuity with the already 
existing corpus of knowledge and, therefore, it becomes all the more essential to be well versed with 
the already existing knowledge.   
 
Hypotheses may be formulated correctly by persons who have rich experiences and academic 
background, but they can never be formulated by those who have poor background knowledge. 
 

• Versatility of intellect:  Hypotheses are also derived through deductive reasoning from a theory.  Such 
hypotheses are called deductive hypotheses.  A researcher may begin a study by selecting one of the 
theories in his own area of interest.  After selecting the particular theory, the researcher proceeds to 
deduce  a  hypothesis  from  this  theory  through  symbolic  logic  or  mathematics.    This  is  possible  only 
when the researcher has a versatile intellect and can make use of it for restructuring his experiences.  
Creative  imagination  is  the  product  of  an  adventure,  sound  attitude  and  agile  intellect.    In  the 
hypotheses formulation, the researcher works on numerous paths.  He has to take a consistent effort 
and develop certain habits and attitudes.  Moreover, the researcher has to saturate himself with all 
possible  information  about  the  problem  and  then  think  liberally  at  it  and  proceed  further  in  the 
conduct of the study. 
• Analogy and other practices.  Analogies also lead the researcher to clues that he might find useful in 
the  formulation  of  hypotheses  and  for  finding  solutions  to  problems.    For  example,  suppose  a  new 
situation  resembles  an  old  situation  in  regard  to  a  factor  X.    If  the  researcher  knows  from  previous 
experience that the old situation is related to other factors Y and Z as well as to X, he reasons that 
perhaps  a  new  situation  is  also  related  to  Y  and  Z.    The  researcher,  however,  should  use  analogies 
with caution as they are not fool proof tools for finding solutions to problems. At times, conversations 
and  consultations  with  colleagues  and  expert  from  different  fields  are  also  helpful  in  formulating 
important and useful hypotheses. 
 

3.8 CHARACTERISTICS OF A GOOD HYPOTHESIS 
 

                Hypothesis must possess the following characteristics: 
i) Hypothesis should be clear and precise.  If the hypothesis is not clear and precise, the inferences 
drawn on its basis cannot be taken as reliable. 
ii) Hypothesis  should  be  capable  of  being  tested.    Some  prior  study  may  be  done  by  researcher  in 
order  to  make  hypothesis  a  testable  one.    A  hypothesis  “is  testable  if  other  deductions  can  be 
made from it which, in turn, can be confirmed or disproved by observation.”   
iii) Hypothesis should state relationship between variables, if it happens to be a relational hypothesis. 
iv) Hypothesis  should  be  limited  in  scope  and  must  be  specific.    A  researcher  must  remember  that 
narrower hypotheses are generally more testable and he should develop such hypotheses. 
v) Hypothesis  should  be  stated  as  far  as  possible  in  most  simple  terms  so  that  the  same  is  easily 
understandable  by  all  concerned.    But  one  must  remember  that  simplicity  of  hypothesis  has 
nothing to do with its significance. 
vi) Hypothesis should be consistent with most known facts i.e. it must be consistent with a substantial 
body of established facts.  In other words, it should be one which judges accept as being the most 
likely. 
vii) The hypotheses selected should be amenable to testing within a reasonable time.  The researcher 
should not select a problem which involves hypotheses that are not agreeable to testing within a 
reasonable and specified time.  He must know that there are problems that cannot be solved for a 
long time to come.  These are problems of immense difficulty that cannot be profitably studied 
because of the lack of essential techniques or measures.  
 
viii) Hypothesis must explain the facts that gave rise to the need for explanation.  This means that by 
using the hypothesis plus other known and accepted generalizations, one should be able to 
deduce the original problem condition.  Thus hypothesis must actually explain what it claims to 
explain, it should have empirical reference. 
 
Check your progress: 
 
1.   What are the different types of hypothesis?  
 

 
2.   List the characteristics of hypothesis.  
 

3.9 HYPOTHESIS TESTING AND THEORY 
 

When the purpose of research is to test a research hypothesis, it is termed as hypothesis‐testing 
research.  It can be of the experimental design or of the non‐experimental design.  Research in which the 
independent variable is manipulated is termed ‘experimental hypothesis‐testing research’ and a research 
in which an independent variable is not manipulated is called ‘non‐experimental hypothesis‐testing 
research’.  
 
Let us get acquainted with relevant terminologies used in hypothesis testing. 
Null hypothesis and alternative hypothesis:   
 
In the context of statistical analysis, we often talk about null hypothesis and alternative 
hypothesis. If we are to compare method A with method B about its superiority and if we proceed on the 
assumption that both methods are equally good, then this assumption is termed as the null hypothesis. 
As against this, we may think that the method A is superior or the method B is inferior, we are then 
stating what is termed as alternative hypothesis.  The null hypothesis is generally symbolized as H0 and 
the alternative hypothesis as Ha. The null hypothesis and the alternative hypothesis are chosen before 
the sample is drawn. Generally, in hypothesis testing we proceed on the basis of null hypothesis, keeping 
the alternative hypothesis in view.  Why so? The answer is that on the assumption that null hypothesis is 
true, one can assign the probabilities to different possible sample results, but this cannot be done if we 
proceed with the alternative hypothesis.  Hence the use of null hypothesis (at times also known as 
statistical hypothesis) is quite frequent. 
 
a) The  level  of  significance:    This  is  very  important  concept  in  the  context  of  hypothesis  testing.    It  is 
always some percentage (usually 5%) which should be chosen with great care, thought and reason.  In 
 case we take the significance level at 5 per cent, then this implies that H0  will be rejected when the 
sampling result (i.e. observed evidence) has a less than 0.05 probability of occurring if H0  is true.  In 
other words, the 5 percent level of significance means that researcher is willing to take as much as a 5 
percent  risk  of  rejecting  the  null  hypothesis  when  it  (H0)  happens  to  be  true.    Thus  the  significance 
level is the maximum value of the probability of rejecting H0 when it is true and is usually determined 
in advance before testing the hypothesis.  
 
b) The  criteria  for  rejecting  the  null  hypothesis  may  differ.    Sometimes  the  null  hypothesis  is  rejected 
only when the quantity of the outcome is so large that the probability of its having occurred by mere 
chance is 1 time out of 100.  We consider the probability of its having occurred by chance to be too 
little and we reject the chance theory of the null hypothesis and take the occurrence to be due to a 
genuine tendency.  On other occasions, we may be bolder and reject the null hypothesis even when 
the quantity of the reported outcome is likely to occur by chance 5 times out of 100.Statistically the 
former is known as the rejection of the null hypothesis at 0.1 level of significance and the latter as the 
rejection at 0.5 level. It may be pointed out that if the researcher is able to reject the null hypothesis, 
he cannot directly uphold the declarative hypothesis.  If an outcome is not held to be due to chance, it 
does  not  mean  that  it  is  due  to  the  very  cause  and  effect  relationship  asserted  in  the  particular 
declarative  statement.    It  may  be  due  to  something  else  which  the  researcher  may  have  failed  to 
control. 
 
c) Decision rule or test of hypothesis:  Given a hypothesis H0 and an alternative hypothesis Ha  we make 
a rule which is known as decision rule according to which we accept H0 (i.e. reject Ha) or reject H0  (ie. 
accept  Ha).    For instance,  if  H0  is  that  a certain lot  is good  (there  are  very few  defective  items  in  it) 
against Ha that the lot is not good (there are too many defective items in it), then we must decide the 
number of items to be tested and the criterion for accepting or rejecting the hypothesis.  We might 
test 10 times in the lot and plan our decision saying that if there are none or only 1 defective item 
among the 10, we will accept H0  otherwise we will reject H0  (or accept  Ha).  This sort of basis is known 
as decision rule. 
 
d) Two‐tailed  and  One‐tailed  tests:      In  the  context  of  hypothesis  testing,  these  two  terms  are  quite 
important and must be clearly understood.  A two‐tailed test rejects the null hypothesis if, say, the 
sample  mean  is  significantly  higher  or  lower  than  the  hypothesized  value  of  the  mean  of  the 
population.    Such  a  test  is  appropriate  when  the  null  hypothesis  is  some  specified  value  and  the 
alternative  hypothesis  is  a  value  not  equal  to  the  specified  value  of  the  null  hypothesis.    In  a  two‐
tailed test, there are two rejection regions, one on each tail of the curve which can be illustrated as 
under: 
 
If the significance level is 5 per cent and the two‐tailed test is to be applied, the probability of the 
rejection area will be 0.05 (equally divided on both tails of the curve as 0.025) and that of the acceptance 
region will be 0.95  
 
            But there are situations when only one‐tailed test is considered appropriate.  A one‐tailed test 
would be used when we are to test, say, whether the population mean is either lower than or higher than 
some hypothesized value. We should always remember that accepting H0, on the basis of sample 
information does not constitute the proof that H0, is true.  We only mean that there is no statistical 
evidence to reject it. 
 

3.10  ERRORS IN TESTING OF HYPOTHESIS 
 

Type I and Type II errors:  in the context of testing of hypotheses, there are basically two types of 
errors we can make.  We may reject H0 when H0 is true and we may accept H0 when in fact H0 is not true.  
The former is known as Type I error and the latter as Type II error.  In other words, Type I error means 
rejection of hypothesis which should have been accepted and Type II error means accepting the 
hypothesis which should have been rejected.  Type I error is denoted by   (alpha) known as   (alpha) error, 
also called the level of significance of test; and Type II error is denoted by ß (beta) known as ß error.  In a 
tabular form the said two errors can be presented as follows: 
 

Table 3.1  Decision 
  Accept H0  Reject H0 
H0 (true)  Correct decision  Type I error (alpha error) 

H0 (false)  Type II error (ß error)  Correct  decision 

 
The probability of Type I error is usually determined in advance and is understood as the level of 
significance of testing the hypothesis.  If type I error is fixed at 5 per cent, it means that there are about 5 
chances in 100 that we will reject H0 when H0 is true.  We can control Type I error just by fixing it at a 
lower level.  For instance, if we fix it at 1 per cent, we will say that the maximum probability of 
committing Type I error would only be 0.01. 
 
But with a fixed sample size, n, when we try to reduce Type I error, the probability of committing 
Type II error increases.  Both types of errors cannot be reduced simultaneously.  There is a trade‐off 
between two types of errors which means that the probability of making one type of error can only be 
reduced if we are willing to increase the probability of making the other type of error.  To deal with this 
trade‐off in business situations, decision‐makers decide the appropriate level of Type I error by 
examining the costs or penalties attached to both types of errors.  If Type I error involves the time and 
trouble of reworking a batch of chemicals that should have been accepted, whereas Type II error means 
taking a chance that an entire group of users of this chemical compound will be poisoned, then in such a 
situation one should prefer a Type I error to a Type II error.  As a result one must set very high level for 
Type I error in one’s testing technique of a given hypothesis.  Hence, in the testing of hypothesis, one 
must make all possible effort to strike an adequate balance between Type I and Type II errors. 
 
Check your progress: 
 
1. Explain the term level of significance?     

 
 

 
2. What are the two types of error in the testing of the hypothesis?  
 

 
 

3.11 SUMMARY 
 

It is important for the researcher to formulate hypotheses before data are gathered.     This is 
necessary for an objective and unbiased study. It should be evident from what you have read so far that 
in order to carry out research; you need to start by identifying a question which demands an answer, or a 
need which requires a solution. The problem can be generated either by an initiating idea, or by a 
perceived problem area. We also studied that there are important qualities of hypotheses which 
distinguish them from other forms of statement. A good hypothesis is a very useful aid to organizing the 
research effort. It specifically limits the enquiry to the interaction of certain variables; it suggests the 
methods appropriated for collecting, analyzing and interpreting the data; and the resultant confirmation 
or rejection of the hypothesis through empirical or experimental testing gives a clear indication of the 
extent of knowledge gained. The hypothesis must be conceptually clear. The concepts utilized in the 
hypothesis should be clearly defined – not only formally but also if possible, operationally. Hypothesis 
testing is the often used strategy for deciding whether a sample data offer such support for a hypothesis 
that generalization can be made.  Thus hypothesis testing enables us to make probability statements 
about population parameter(s).   
BIBLIOGRAPHY 
 
1. Best  J.W,  Kahn  J.V  ;(  2009);  Research  in  education,  tenth  edition,  Dorling  Kindersley  (India)  Pvt  Ltd, 
New Delhi. 
2. Wiersma W , Jurs S G;(2009); research methods in education an introduction, ninth edition, Pearson 
education, Dorling Kindersley (India) Pvt Ltd, New Delhi. 
3. Kothari C.R; (2009) Research methodology methods and techniques, second edition, New Delhi, New 
age international (P) Ltd publishers. 
4. Gupta  S;  (2007);  Research  methodology  and  statistical  techniques;  New  Delhi,  Deep  and  Deep 
publication Pvt Ltd.  
5. McBurney, D.H; White T,L; (2007); Research methods, seventh edition; Delhi, Akash press. 
6. Kaul,  L;  (2004);  Methodology  of  educational  research,  third  edition,  New  Delhi,  UBS  Publishers’ 
Distributors Pvt Ltd. 
 
 

4
 

 
SAMPLING 
 

Unit Structure  

 
4.0   Objectives 
4.1   Introduction 
4.2   Concept of Universe sample and sampling  
4.3   Need for sampling 
4.4   Advantages and Disadvantages of sampling 
4.5   Characteristics of a good sample 
4.6   Techniques of sampling 
4.7   Types of probability sampling 
4.8   Types of Non‐probability sampling 
4.9   Let us sum up 
 

4.0 OBJECTIVES : 
 

After reading this unit the student will be able to : 

• Define universe, sample and sampling  
• State the need of sampling 
• List the advantages and disadvantages of sampling 
• State the characteristics of a good sample 
• Differentiate between techniques of sampling 
• Explain types of probability & Non‐ probability sampling 
 
4.1 INTRODUCTION : 

    The researcher is concerned with the generalizability of the data beyond the sample.  For studying 
any  problem  it  is  impossible  to  study  the  entire  population.    It  is  therefore  convenient  to  pick  out  a 
sample  out  of  the  universe  proposed  to  be  covered  by  the  study.    The  process  of  sampling  makes  it 
possible to draw valid inferences or generalizations on the basis of careful observation of variables within 
a small proportion of the population. 

4.2     CONCEPT OF UNIVERSE, SAMPLE AND SAMPLING : 

    Universe  or  Population  :  It  refers  to  the  totality  of  objects  or  individuals  regarding  which 
inferences are to be made in a sampling study.  

Or 

      It refers to the group of people, items or units under investigation and includes every individual. 

  First, the population is selected for observation and analysis. 

Sample : It is a collection consisting of a part or subset of the objects or individuals of population which is 
selected  for  the  purpose,  representing  the  population  sample  obtained  by  collecting  information  only 
about some members of a population. 

Sampling : It is the process of selecting a sample from the population.  For this population is divided into 
a number of parts called Sampling Units. 

4.3 NEED FOR SAMPLING : 

• Large population can be conveniently covered. 
• Time, money and energy is saved. 
• Helpful when units of area are homogenous. 
• Used when percent accuracy is not acquired. 
• Used when the data is unlimited. 
 
4.4     ADVANTAGES AND DISADVANTAGES OF SAMPLING : 
 

Advantages of Sampling : 

• Economical :  Manageable sample will reduce the cost compare to entire population. 
• Increased speed :  The process of research like collection of data, analysis and Interpretation of data 
etc take less time than the population. 
• Greater  Scope  :    Handling  data  becomes  easier  and  manageable  in  case  of  a  sample.    Moreover 
comprehensive scope and flexibility exists in the case of a sample. 
• Accuracy :  Due to limited area of coverage, completeness and accuracy is possible.  The processing of 
data is done accurately producing authentic results. 
• Rapport :  Better rapport is established with the respondents, which helps in validity and reliability of 
the results. 
 

Disadvantages of Sampling : 
 

• Biasedness :  Chances of biased selection leading to erroneous conclusions may prevail.  Bias in the 
sample may be due to faulty method of selection of individuals or the nature of phenomenon itself. 
• Selection  of  true  representative  sample  :    It  the  problem  under  study  is  of  a  complex  nature,  it 
becomes difficult to select a true representative sample, otherwise results will not be accurate & will 
be usable. 
• Need  for  specialized  knowledge  :  The    researcher  needs  knowledge,  training  and  experience  in 
sampling technique, statistical analysis and calculation of probable error.  Lack of those may lead to 
serious mistakes. 
• Changeability of units :   If the units of population are not homogeneous, the sampling technique will 
be unscientific.  At times, all the individuals may not be accessible or may be uncooperative. In such a 
case, they have o be replaced.  This introduces a change in the subjects to be studied. 
• Impossibility  of  sampling  :    Sometimes  population  is  too  small  or  too  heterogeneous  to  select  a 
representative  sample.    In  such  cases  ‘census  study’  is  the  alternative  (Information  about  each 
member  of  the  population)  Sampling  error  also  comes  because  of  expectation  of  high  standard  of 
accuracy. 
 

4.5 CHARACTERISTICS OF A GOOD SAMPLE :   

A good sample should possess the following characteristics : 

• A true representative of the population  
• Free from error due to bias 
• Adequate in size for being reliable 
• Units of sample should be independent and relevant 
• Units of sample should be complete precise and up to date 
• Free from random sampling error  
• Avoiding substituting the original sample for convenience. 
Check Your Progress ‐ I 

Q.1  Define the following 

    (a)  Sample 

    (b)  Sampling 

Q.2  Write any three points for the following. 

    (a)  Need for sampling 

    (b)  Advantages of sampling 

    (c)  Disadvantages of sampling 

    (d)  Characteristics of a good sample 

 
4.6 TECHNIQUES OF SAMPLING :   

    There are different types of sampling techniques based on two factors viz.  (1)  the representation 
basis  and  (2)    the  element  selection  technique  on  the  representation  basis.  The  sample  may  be 
probability  sampling or  it  may  be  non‐probability  sampling.    On the  element  basis,  the  sample may  be 
either unrestricted or restricted.  Here we will discuss about two types of sampling viz. 

    (a)  Probability Sampling and  

    (b)  Non‐Probability Sampling. 

Difference between Probability and Non‐ Probability Sampling :  

(1) A  probability  sample  is  one  in  which  each  member  of  the  population  has  an  equal  chance  of  being 
selected  but  in  a  non‐probability  sample,  a  particular  member  of  the  population  being  chosen  is 
unknown. 

(2) In probability sampling, randomness is the element of control. In non‐probability sampling, it relies on 
personal judgment. 

4.7 TYPES OF PROBABILITY SAMPLING : 

Following are the types of probability sampling  

1)  Simple random sampling 

2)  Systematic sampling 

3)  Stratified sampling 

4)  Cluster sampling 

5)  Multi stage sampling 

Simple  Random  Sampling  :  In  this  all  members  have  the  same  chance  (probability)  of  being  selected.  
Random method provides an unbiased cross selection of the population.  For Example, we wish to draw a 
sample of 50 students from a population of 400 students.  Place all 400 names in a container and draw 
out 50 names one by one. 

 
Systematic  Sampling  :  Each  member  of  the  sample  comes  after  an  equal  interval  from  its  previous 
50 1
member.  For Example, for a sample of 50 students, the sampling fraction is  =  i.e. select one 
400 8
student out of every eight students in the population.  The starting points for the selection is chosen at 
random. 

Stratified  Sampling  :    The  population  is  divided  into  smaller  homogenous  group  or  strata  by  some 
characteristic and from each of these strata at random members are selected. For Example, population is 
Christian community of greater Mumbai region.  It is divided into strata as professionals, skilled workers, 
Labourers  and  Managers  then  from  each  strata  sampling  fraction.  i.e. 
Ѕample size
× Τotal No. in the strata   is  chosen.    Finally  from  each  stratum  using  simple  random  or 
Τotal population
systematic sample method is used to select final sample. 

    There are 400 Christians in greater Mumbai.  There are 100 professionals, 200 skilled workers, 80 
labourers and 120 Managers.  If the sample size is 80,  then from each stratum sampling fraction is  

80
Professionals = × 100 = 20  
400

200
Skilled workers = × 100 = 50  
400

80
Labourers = × 100 = 20  
400

120
Managers = × 100 = 30  
400

From each stratum select randomly or systematically. 

Cluster  Sampling  (Area  Sampling)  :  A  researcher  selects  sampling  units  at  random  and  then  does 
complete  observation  of  all  units  in  the  group.    For  example,  your  research  involves  kindergarten 
schools.  Select randomly 15 schools.  Then study all the children of 15 schools.  In cluster sampling the 
unit  of  sampling  consists  of  multiple  cases.    It  is  also  known  as  area  sampling,  as  the  selection  of 
individual member is made on the basis of place residence or employment.   
 

Multistage Sampling : The sample to be studied is selected at random at different stages. For example, 
we need to select a  sample  of middle class working couples in aharashtra state.  The first stage will be 
randomly  selecting  a  specific  number  of  districts  in  a  state.    The  second  stage  involves  selecting 
randomly a specific number of rural and urban areas for the study. At the third stage, from each area, a 
specific number of  middle class families will be selected and at the last stage, working couples will be 
selected from these families. 

4.8 TYPES NON‐PROBABILITY SAMPLING : 

The following are techniques of non‐probability sampling :  

a)  Purposive Sampling 

b)  Convenience Sampling 

c)  Quota Sampling  

d)  Snowball Sampling 

A)  Purposive Sampling : In this sampling method, the researcher selects a "typical group" of individuals 
who  might  represent  the  larger  population  and  then  collects  data  from  this  group.  For  example,  if  a 
researcher wants to survey the attitude towards the teaching profession of teachers teaching students 
from lower socio‐economic stratum, he or she might survey the teachers teaching in schools catering to 
students from slums (more specifically, teachers teaching in Municipal schools) with  the assumption that 
since all teachers teaching in Municipal schools cater to students from the lower socio‐economic stratum, 
they are representative of all the teachers teaching students from lower socio‐economic stratum.   
 

B)  Convenience  Sampling  :  It  refers  to  the  procedures  of  obtaining  units  or  members  who  are  most 
conveniently  available.  It  consists  of  units  which  are  obtained  because  cases  are  readily  available.  In 
selecting  the  incidental  sample,  the  researcher  determines  the  required  sample  size  and  then  simply 
collects data on that number of individuals who are available easily. 

     

C)  Quota Sampling : The selection of the sample is made by the researcher, who  decides the quotas  for 
selecting sample from specified sub groups of the population.  Here, the researcher first identifies those 
categories which he or she feels are important to ensure the representativeness of the population, then 
establishes  a  sample  size  for  each  category,  and  finally  selects  individuals  on  an  availability  basis.  For 
example,  an  interviewer  might  be  need  data  from  40  adults  and  20  adolescents  in  order  to  study 
students’  television  viewing  habits.  He  therefore,  will  go  out  and  select  20  adult  men  and  20  adult 
women,  10  adolescent  girls  and  10  adolescent  boys  so  that  they  could  interview  them  about  their 
students’ television viewing habits. 
 

Snowball Sampling : In snowball sampling, the researcher identifying and selecting available respondents 
who meet the criteria for inclusion in his/her study. After the data have been collected from the subject, 
the researcher asks for a referral of other individuals, who would also meet the criteria and represent the 
population of concern.  

Check Your Progress ‐ II 

Q.1)  Differentiate between probability and non‐probability sampling. 

Q.2)  Discuss the types of probability sampling. 

Q.3)  Discuss the types of non‐probability sampling. 

4.9 LET US SUM UP : 

    In  this  unit  we  discussed  the  concept  of  population,  sample  and  sampling.    Need  of  sampling 
advantages and disadvantages of sampling were discussed and also Characteristics of a good sample are 
elaborated.  In the second part, the types of probability and non‐probability sampling were detailed. 

References : 

1)  Kulbir Singh Siddhu (1992), Methodology of Research in Education, Sterling Publishers Private Limited 
pg, 252. 

2)  C.R. Kothari (1991), Research Methodology – Methods and Techniques, wiley Eaetern Limited, pg 68. 
 5
DESCRIPTIVE RESEARCH

Unit Structure

5.0 Objectives
5.1 Meaning of Descriptive Research
5.2 Co relational Research
5.3 Causal-Comparative Research
5.4 Document Analysis
5.5 Ethnography
5.6 Case Study
5.7 Analytical Method.

5.0 OBJECTIVES :

After reading this unit, the student will be able to :

(a) State the nature of descriptive research

(b) Explain how to conduct correlational research
(c) Explain how to conduct correlational research
(d) Explain how to conduct causal-comparative research
(e) Explain how to conduct case study research
(f) Explain the concept of documentary research
(g) Explain how to conduct ethnographic research
(h) Explain the concept of analytical research

5.1 NATURE OF DESCRIPTIVE RESEARCH:

The descriptive research attempts to describe, explain and interpret conditions of the present i.e.
“what is’. The purpose of a descriptive research is to examine a phenomenon that is occurring at a specific
place(s) and time. A descriptive research is concerned with conditions, practices, structures, differences or
relationships that exist, opinions held, processes that are going on or trends that are evident.
Types of Descriptive Research Methods

In the present unit, the following descriptive research methods are described in detail:

1. Correlational Research
2. Causal-Comparative Research
3. Case Study
4. Ethnography
 5. Document Analysis
6. Analytical Method.

5.2 CO-RELATIONAL METHOD :

Correlational research describes what exists at the moment (conditions, practices, processes,
structures etc.) and is therefore, classified as a type of descriptive method. Nevertheless, these conditions,
practices, processes or structures described are markedly different from the way they are usually described
in a survey or an observational study.

Correlational research comprises of collecting data to determine whether, and to what extent, a
relationship exists between two or more quantifiable variables. Correlational research uses numerical data
to explore relationships between two or more variables. The degree of relationship is expressed in terms of
a coefficient of correlation. If the relationship exists between variables, it implies that scores on one
variable are associated with or vary with the scores on another variable. The exploration of relationship of
the relationship between variables provides insight into the nature of the variables themselves as well as an
understanding of their relationships. If the relationships are substantial and consistent, they enable a
researcher to make predictions about the variables.

Correlational research is aimed at determining the nature, degree and direction of relationships
between variables or using these relationships to make predictions. Correlational studies typically
investigate a number of variables expected to be related to a major, complex variable. Those variables
which are not found to be related to this major, complex variable are omitted from further analysis. On the
other hand, those variables which are found to be related to this major, complex variable are further
analysed in a causal-comparative or experimental study so as to determine the exact nature of the
relationship between them.
In a correlational study, hypotheses or research questions are stated at the beginning of the study.
The null hypotheses are often used in a correlational study.

Correlational study does not specify cause-and-effect relationships between variables under
consideration. It merely specifies concomitant variations in the scores on the variables. For example, there
is a strong relationship between students’ scores on academic achievement in Mathematics and their scores
on academic achievement in Science. This does not suggest that one of these variables is the cause and the
other is the effect. In fact, a third variable, viz., students’ intelligence could be the cause of students’
academic achievement in both, Mathematics and Science.

Steps of a Correlational Research

1. Selection of a Problem: Correlational study is designed (a) to determine whether and how a set of
variables are related, or (b) to test the hypothesis of expected relationship between among the set of
two or more variables. The variables to be included in the study need to be selected on the basis of a
sound theory or prior research or observation and experience. There has to be some logical
connection between the variables so as to make interpretations of the findings of the study more
meaningful, valid and scientific. A correlational study is not done just to find out what exists: it is
done for the ultimate purpose of explanation and prediction of phenomena. If a correlational study
is done just to find out what exists, it is usually known as a ‘shot gun’ approach and the findings of
such a study are very difficult to interpret.

2. Selection of the Sample and the Tools: The minimum acceptable sample size should be 30, as
statistically, it is regarded as a large sample. The sample is generally selected using one of the
acceptable sampling methods. If the validity and the reliability of the variables to be studied are
low, the measurement error is likely to be high and hence the sample size should be large. Thus it is
necessary to ensure that valid and reliable tools are used for the purpose of collecting the data.
 Moreover, suppose you are studying the relationship between classroom environment and academic
achievement of students. If your tool measuring classroom environment focuses only on the
physical aspects of the classroom and not its psycho-social aspects, then your findings would
indicate a relationship only between academic achievement of students and the physical aspects of
the classroom environment and not the entire classroom environment since the physical aspects of
the classroom environment is not the only comprehensive and reliable measure of classroom
environment. Thus the measurement instruments should be valid and reliable.

3. Design and Procedure: The basic design of a correlational study is simple. It requires scores
obtained on two or more variables from each unit of the sample and the correlation coefficient
between the paired scores is computed which indicates the degree and direction of the relationship
between variables.

4. Interpretation of the Findings: In a study designed to explore or test hypothesized relationships, a

correlation coefficient is interpreted in terms of its statistical significance.

Co relational research is of the following two types:

(a) Relationship Studies: These attempt to gain insight into variables that are related to complex
variables such as academic performance, self-concept, stress, achievement motivation or creativity.

(b) Prediction Studies: These are conducted to facilitate decisions about individuals or to aid in
various types of selection. They are also conducted to determine predictive validity of measuring
tools as well as to test variables hypothesized to be predictors of a criterion variable.

Some questions that could be examined through correlational research are as follows:
1. How is job satisfaction of a teacher related to the extent of autonomy available in job?
2. Is there a relationship between Socio-Economic Status of parents and their involvement with the
school?
3. How well do Common Entrance Test Scores for admission to B.Ed. reflect / predict teacher
effectiveness?

Check Your Progress - I

(a) State the meaning of correlational research.

 
 

(b) Explain the steps of correlational research.

 
 

 
 
 

5.3 CAUSAL-COMPARATIVE RESEARCH :

It is a type of descriptive research since it describes conditions that already exist. It is a form of
investigation in which the researcher has no direct control over independent variable as its expression has
already occurred or because they are essentially non-manipulable. It also attempts to identify reasons or
causes of pre-existing differences in groups of individuals i.e. if a researcher observes that two or more
groups are different on a variable, he tries to identify the main factor that has led to this difference.
Another name for this type of research is ex post facto research (which in Latin means “after the fact”)
since both the hypothesised cause and the effect have already occurred and must be studied in retrospect.

Causal-comparative studies attempt to identify cause-effect relationships, correlational studies do

not. Causal-comparative studies involve comparison, correlational studies involve relationship. However,
neither method provides researchers with true experimental data. On the other hand, causal-comparative
and experimental research both attempt to establish cause-and-effect relationships and both involve
comparisons. In an experimental study, the researcher selects a random sample and then randomly divides
the sample into two or more groups. Groups are assigned to the treatments and the study is carried out.
However, in causal-comparative research, individuals are not randomly assigned to treatment groups
because they already were selected into groups before the research began. In experimental research, the
independent variable is manipulated by the researcher, whereas in causal-comparative research, the groups
are already formed and already different on the independent variable.

Inferences about cause-and-effect relationships are made without direct intervention, on the basis of
concomitant variation of independent and dependent variables. The basic causal-comparative method starts
with an effect and seeks possible causes. For example, if a researcher observes that the academic
achievement of students from different schools. He may hypothesise the possible cause for this as the type
of management of schools, viz. private-aided, private-unaided, or government schools (local or state or any
other). He therefore decides to conduct a causal-comparative research in which academic achievement of
students is the effect that has already occurred and school types by management is the possible
hypothesised cause. This approach is known as retrospective causal-comparative research since it starts
with the effects and investigates the causes.

In another variation of this type of research, the investigator starts with a cause and investigates its
effect on some other variable. i.e. such research is concerned with the question ‘what is the effect of X on
Y when X has already occurred?’ For example, what long-term effect has occurred on the self-concept of
students who are grouped according to ability in schools? Here, the investigator hypothesises that students
who are grouped according to ability in schools are labelled ‘brilliant’, ‘average’ or ‘dull’ and this over a
period of time could lead to unduly high or unduly poor self-concept in them. This approach is known as
prospective causal-comparative research since it starts with the causes and investigates the effects.
However, retrospective causal-comparative studies are far more common in educational research.

Causal-comparative research involves two or more groups and one independent variable. The goal
of causal-comparative research is to establish cause-and-effect relationships just like an experimental
research. However, in causal-comparative research, the researcher is able to identify past experiences of
the subjects that are consistent with a ‘treatment’ and compares them with those subjects who have had a
different treatment or no treatment. The causal-comparative research may also involve a pre-test and a
post-test. For instance, a researcher wants to compare the effect of “Environmental Education” in the B.Ed.
syllabus on student-teachers’ awareness of environmental issues and problems attitude towards
environmental protection. Here, a researcher can develop and administer a pre-test before being taught the
paper on “Environmental Education” and a post-test after being taught the same. At the same time, the pre-
test as well as the post-test are also administered to a group which was not taught the paper on
“Environmental Education”. This is essentially a non-experimental research as there is no manipulation of
the treatment although it involves a pre-test and a post-test. In this type of research, the groups are not
randomly assigned to exposure to the paper on “Environmental Education”. Thus it is possible that other
variables could also affect the outcome variables. Therefore, in a causal-comparative research, it is
important to think whether differences other than the independent variable could affect the results.

In order to establish cause-and-effect in a causal-comparative research, it is essential to build a

convincing rational argument that the independent variable is influencing the dependent variable. It is also
essential to ensure that other uncontrolled variables do not have an effect on the dependent variable. For
this purpose, the researcher should try to draw a sample that minimises the effects of other extraneous
variables. According to Picciano, “In stating a hypothesis in a causal comparative study, the word “effect”
is frequently used”.

Conducting a Causal-Comparative Study

Although the independent variable is not manipulated, there are control procedures that can be
exercised to improve interpretation of results.

Design and Procedure

The researcher selects two groups of participants, accurately referred to as comparison groups. These
groups may differ in two ways as follows:
(i) One group possesses a characteristic that the other does not.
(ii) Each group has the characteristic, but to differing degrees or amounts.
(iii) Definition and selection of the comparison groups are very important parts of the causal-
comparative procedure.
(iv) The independent variable differentiating the groups must be clearly and operationally defined,
since each group represents a different population.
(v) In causal-comparative research the random sample is selected from two already existing
populations, not from a single population as in experimental research.
(vi) As in experimental studies, the goal is to have groups that are as similar as possible on all
relevant variables except the independent variable.
(vii) The more similar the two groups are on such variables, the more homogeneous they are on
everything but the independent variable.

Control Procedures
• Lack of randomization, manipulation, and control are all sources of weakness in a causal-
comparative study.
• Random assignment is probably the single best way to try to ensure equality of the groups.
• A problem is the possibility that the groups are different on some other important variable
(e.g. gender, experience, or age) besides the identified independent variable.

Matching
• Matching is another control technique.
 • If a researcher has identified a variable likely to influence performance on the dependent variable,
the researcher may control for that variable by pair-wise matching of participants.
• For each participant in one group, the researcher finds a participant in the other group with the same
or very similar score on the control variable.
• If a participant in either group does not have a suitable match, the participant is eliminated from the
study.
• The resulting matched groups are identical or very similar with respect to the identified extraneous
variable.
• The problem becomes serious when the researcher attempts to simultaneously match participants on
two or more variables.
Comparing Homogeneous Groups or Subgroups
• To control extraneous variables, groups that are homogeneous with respect to the extraneous
variable are compared.
• This procedure may lower the number of participants and limit the generalisability of the findings.
• A similar but more satisfactory approach is to form subgroups within each group that represent all
levels of the control variable.
• Each group might be divided into two or more subgroups on the basis of high, average, and low
levels of ‘Independent variable’.
• Suppose the independent variable in the study is students’ IQ. The subgroups then will comprise of
high, average, and low levels of IQ. The existence of comparable subgroups in each group controls
for IQ.
• In addition to controlling for the variable, this approach also permits the researcher to determine
whether the independent variable affects the dependent variable differently at different levels of the
control variable.
• The best approach is to build the control variable right into the research design and analyze the
results in a statistical technique called factorial analysis of variance.
• A factorial analysis allows the researcher to determine the effect of the independent variable and the
control variable on the dependent variable both separately and in combination.
• It permits determination of whether there is interaction between the independent variable and the
control variable such that the independent variable operates differently at different levels of the
control variable.

Independent variables in a causal-comparative research can be of following types:

Type of Variable Examples

Organismic Variables Age

Gender
Religion
Caste
Ability Variables Intelligence
Scholastic Ability
Specific Aptitudes
 

Personality Variables Anxiety Level

Stress-proneness
Aggression Level
Emotional Intelligence
Introversion / Extroversion
Self-Esteem
Self-Concept
Academic or Vocational Aspirations
Brain Dominance
Learning, Cognitive or Thinking Styles
Psycho-Social Maturity
Home Background Home Environment
Related Variables
Socio-Economic Status
Educational Background of Parents
Economic Background of Parents
Employment Status of Parents
Single Parent v/s Both Parents
Employment Status of Mother (Working or
Non- Working)
Birth Order
No. of Siblings
School Related Variables School Environment
Classroom Environment
Teacher Personality
Teaching Style
Leadership Style
School Type by Management ( Private-aided
v/s Private-unaided v/s Government)
School Type by Gender( Single-sex v/s Co-
educational)
School Type by Denomination (Run by a non-
religious organisation v/s Run by a religious
organisation whose one of the objectives is to
propagate a specific religion.)
School Type by Board Affiliation (SSC,
CBSE, ICSE, IB, IGCSE)
School Size
Per Student Expenditure
Socio-Economic Context of the School
The Value of Causal-Comparative Research: In a large majority of educational research especially in
the fields of sociology of education and educational psychology, it is not possible to manipulate
independent variables due to ethical considerations especially when one is dealing with variables such as
anxiety, intelligence, home environment, teacher personality, negative reinforcement, equality of
opportunity and so on. It is also not possible to control such variables as in an experimental research. For
studying such topics and their influence on students, causal-comparative method is the most appropriate.
The Weaknesses of Causal-Comparative Research: There are three major limitations of causal-
comparative research. These include, (a) lack of control or the inability to manipulate independent
variables methodologically, (b) the lack of power to assign subjects randomly to groups and (c) the danger
of inappropriate interpretations. The lack of randomization, manipulation, and control factors make it
difficult to establish cause-and-effect relationships with any degree of confidence.

The statistical techniques used to compare groups in a causal-comparative research include the t-test
when two groups are to be compared and ANOVA when more than two groups are to be compared. The
technique of ANCOVA may also be used in case some other variables likely to influence the dependent
variable need to be controlled statistically. Sometimes, chi square is also used to compare group
frequencies, or to see if an event occurs more frequently in one group than another.

Use of Analysis of Covariance (ANCOVA) : It is used to adjust initial group differences on

variables used in causal-comparative and experimental research studies. Analysis of covariance adjusts
scores on a dependent variable for initial differences on some other variable related to performance on the
dependent. Suppose we were doing a study to compare two methods, X and Y, of teaching sixth standard
students to solve mathematical problems. Covariate analysis statistically adjusts the scores of method Y to
remove the initial advantage so that the results at the end of the study can be fairly compared as if the two
groups started equally.

Check Your Progress - II

(a) State the meaning of causal-comparative research.

(b) Explain the steps and procedure of conducting causal-comparative research.

 

 
 

(c) Explain the strengths and weaknesses of causal-comparative research.

 
 

(d) Give examples of causal-comparative research in education.

5.4 DOCUMENTARY ANALYSIS:

Documentary Analysis is closely related to historical research since in such surveys we study the
existing documents. But it is different from historical research in which our emphasis is on the study of the
past; and in the descriptive research we emphasise on the study of the present. Descriptive research in the
field of education may focus on describing the existing school practices, attendance rate of the students,
health records, and so on.

The method of documentary analysis enables the researcher to include large amounts of textual
information and systematically identify its properties. Documentary analysis today is a widely used
research tool aimed at determining the presence of certain words or concepts within texts or sets of texts.
Researchers quantify and analyze the presence, meanings and relationships of such words and concepts,
then make inferences about the messages within the texts, the writer(s), the audience and even the culture
and time of which these are a part. Documentary analysis could be defined as a research technique for the
objective, systematic, and quantitative description of manifest content of communications. It is a technique
for making inferences by objectively and systematically identifying specified characteristics of messages.
The technique of documentary analysis is not restricted to the domain of textual analysis, but may be
applied to other areas such as coding student drawings or coding of actions observed in videotaped studies,
analyzing past documents such as memos, minutes of the meetings, legal and policy statements and so on.
In order to allow for replication, however, the technique can only be applied to data that are durable in
nature. Texts in documentary analysis can be defined broadly as books, book chapters, essays, interviews,
discussions, newspaper headlines and articles, historical documents, speeches, conversations, advertising,
theater, informal conversation, or really any occurrence of communicative language. Texts in a single
study may also represent a variety of different types of occurrences.

Documentary analysis enables researchers to sift through large amount of data with comparative
ease in a systematic fashion. It can be a useful technique for allowing one to discover and describe the
focus of individual, group, institutional or social attention. It also allows inferences to be made which can
then be corroborated using other methods of data collection. Much documentary analysis research is
motivated by the search for techniques to infer from symbolic data what would be too costly, no longer
possible, or too obtrusive by the use of other techniques. These definitions illustrate that documentary
analysis emphasises an integrated view of speech/texts and their specific contexts. Document analysis is
the systematic exploration of written documents or other artefacts such as films, videos and photographs.
In pedagogic research, it is usually the contents of the artefacts, rather than say, the style or design, that are
of interest.
Why analyse documents?

Documents are an essential element of day-to-day work in education. They include:

• Student essays
• Exam papers
• Minutes of meetings
• Module outlines
• Policy documents

In some pedagogic research, analysis of relevant documents will inform the investigation. If used to
triangulate, or give another perspective on a research question, results of document analysis may
complement or refute other data. For example, policy documents in an institution may be analysed and
interviews with staff or students and observation of classes may suggest whether or not new policies are
being implemented. A set of data from documents, interviews and observations could contribute to a case
study of a particular aspect of pedagogy.

How can documents be analysed?

The content of documents can be explored in systematic ways which look at patterns and themes
related to the research question(s). For example, in making a case study of deep and surface learning in a
particular course, the question might be

'How has deep learning been encouraged in this course in the last three years?'

Minutes of course meetings could be examined to see whether or how much this issue has been
discussed; Student handouts could be analysed to see whether they are expressed in ways which might
encourage deep learning. Together with other data-gathering activities such as student questionnaires or
observation of classes, an action research study might then be based on an extended research question so
that strategies are implemented to develop deep learning.

In the example of deep learning, perhaps the most obvious way to analyse the set of minutes would
be to use a highlighting pen every time the term 'deep learning' was used. You might also choose to
highlight 'surface learning' a term with an implied relationship to deep learning. You might also decide,
either before starting the analysis, or after reading the documents, that there are other terms or inferences
which imply an emphasis on deep learning. You might therefore go through the documents again, selecting
additional references.

The levels of analysis will vary but a practitioner-researcher will need to be clear and explicit about
the rationale for, and the approach to, selection of content.

Advantages and disadvantages of document analysis

Robson (2002) points out the advantages and disadvantages of content analysis. An advantage is
that documents are unobtrusive and can be used without imposing on participants; they can be checked and
re-checked for reliability.

A major problem is that documents may not have been written for the same purposes as the research
and therefore conclusions will not usually be possible from document analysis alone.

Check Your Progress - III

(a) State the meaning of documentary research.

(b) Explain the applications of documentary research.

5.5 ETHNOGRAPHY:

Meaning

Ethnographic studies are usually holistic, founded on the idea that human beings are best
understood in the fullest possible context, including the place where they live, the improvements they have
made to that place, how they make a living and gather food, housing, energy and water for themselves,
what their marriage customs are, what language(s) they speak and so on. Ethnography is a form of research
focusing on the sociology of meaning through close field observation of socio-cultural phenomena.
Typically, the ethnographer focuses on a community (not necessarily geographic, considering also work,
leisure, classroom or school groups and other communities). Ethnography may be approached from the
point of view of art and cultural preservation and as a descriptive rather than analytic endeavour. It
essentially is a branch of social and cultural anthropology. The emphasis in ethnography is on studying an
entire culture.The method starts with selection of a culture, review of the literature pertaining to the
culture, and identification of variables of interest - typically variables perceived as significant by members
of the culture. Ethnography is an enormously wide area with an immense diversity of practitioners and
methods. However, the most common ethnographic approach is participant observation and unstructured
interviewing as a part of field research. The ethnographer becomes immersed in the culture as an active
participant and records extensive field notes. In an ethnographic study, there is no preset limit of what will
be observed and interviewed and no real end point in as is the case with grounded theory.

Hammersley and Atkinson define ethnography as, "We see the term as referring primarily to a
particular method or sets of methods. In its most characteristic form it involves the ethnographer
participating, overtly or covertly, in people's lives for an extended period of time, watching what happens,
listening to what is said, asking questions—in fact, collecting whatever data are available to throw light on
the issues that are the focus of the research. Johnson defines ethnography as "a descriptive account of
social life and culture in a particular social system based on detailed observations of what people actually
do."
Assumptions in an Ethnographic Research

According to Garson, these are as follows:

a. Ethnography assumes that the principal research interest is primarily affected by community cultural
understandings. The methodology virtually assures that common cultural understandings will be
identified for the research interest at hand. Interpretation is apt to place great emphasis on the causal
importance of such cultural understandings. There is a possibility that an ethnographic focus will
overestimate the role of cultural perceptions and underestimate the causal role of objective forces.
b. Ethnography assumes an ability to identify the relevant community of interest. In some settings, this
can be difficult. Community, formal organization, informal group and individual-level perceptions
may all play a causal role in the subject under study and the importance of these may vary by time,
place and issue. There is a possibility that an ethnographic focus may overestimate the role of
community culture and underestimate the causal role of individual psychological or of sub-
community (or for that matter, extra-community) forces.
c. Ethnography assumes that the researcher is capable of understanding the cultural mores of the
population under study, has mastered the language or technical jargon of the culture and has based
findings on comprehensive knowledge of the culture. There is a danger that the researcher may
introduce bias toward perspectives of his or her own culture.
d. While not inherent to the method, cross-cultural ethnographic research runs the risk of falsely
assuming that given measures have the same meaning across cultures.

Characteristics of Ethnographic Research:

According to Hammersley and Sanders, ethnography is characterized by the following features :

(a) People's behaviour is studied in everyday contexts.

(b) It is conducted in a natural setting.
(c) Its goal is more likely to be exploratory rather than evaluative.
(d) It is aimed at discovering the local person’s or “native’s” point of view, wherein, the native may be a
consumer or an end-user.
(e) Data are gathered from a wide range of sources, but observation and/or relatively informal
conversations are usually the principal ones.
(f) The approach to data collection is unstructured in that it does not involve following through a
predetermined detailed plan set up at the beginning of the study nor does it determine the categories
that will be used for analysing and interpreting the soft data obtained. This does not mean that the
research is unsystematic. It simply means that initially the data are collected as raw form and a wide
amount as feasible.
(g) The focus is usually a single setting or group of a relatively small size. In life history research, the
focus may even be a single individual.
(h) The analysis of the data involves interpretation of the meanings and functions of human actions and
mainly takes the form of verbal descriptions and explanations, with quantification and statistical
analysis playing a subordinate role at most.
(i) It is cyclic in nature concerning data collection and analysis. It is open to change and refinement
throughout the process as new learning shapes future observations. As one type of data provides new
information, this information may stimulate the researcher to look at another type of data or to elicit
confirmation of an interpretation from another person who is part of the culture being studied.
Guidelines for Conducting Ethnography

Following are some broad guidelines for conducting fieldwork:

1. Be descriptive in taking field notes. Avoid evaluations.

2. Collect a diversity of information from different perspectives.
3. Cross-validate and triangulate by collecting different kinds of data obtained using observations,
interviews, programme documentation, recordings and photographs.
4. Capture participants' views of their own experiences in their own words. Use quotations to represent
programme participants in their own terms.
5. Select key informants carefully. Draw on the wisdom of their informed perspectives, but keep in
mind that their perspectives are limited.
6. Be conscious of and perceptive to the different stages of fieldwork. (a) Build trust and rapport at the
entry stage. Remember that the researcher-observer is also being observed and evaluated. (b) Stay
attentive and disciplined during the more routine middle-phase of fieldwork. (c) Focus on pulling
together a useful synthesis as fieldwork draws to a close. (d) Be well-organized and meticulous in
taking detailed field notes at all stages of fieldwork. (e) Maintain an analytical perspective grounded
in the purpose of the fieldwork: to conduct research while at the same time remaining involved in
experiencing the observed setting as fully as possible. (f) Distinguish clearly between description,
interpretation and judgment. (g) Provide formative feedback carefully as part of the verification
process of fieldwork. Observe its effect. (h) Include in your field notes and observations reports of
your own experiences, thoughts and feelings. These are also field data. Fieldwork is a highly
personal experience. The meshing of fieldwork procedures with individual capabilities and
situational variation is what makes fieldwork a highly personal experience. The validity and
meaningfulness of the results obtained depend directly on the observer's skill, discipline, and
perspective. This is both the strength and weakness of observational methods.

Techniques Used in Conducting Ethnography

These include the following :

A. Listening to conversations and interviewing. The researcher needs to make notes or audio-record
these.
B. Observing behaviour and its traces, making notes and mapping patterns of behaviour, sketching of
relationship between people, taking photographs, video-recordings of daily life and activities and
using digital technology and web cameras.

Stages in Conducting Ethnography

According to Spradley, following are the stages in conducting an ethnographic study :

1. Selecting an ethnographic project.

2. Asking ethnographic questions and collecting ethnographic data.
3. Making an ethnographic record.
4. Analysing ethnographic data and conducting more research as required.
5. Outlining and writing an ethnography.

Steps of Conducting Ethnography

 According to Spradley, ethnography is a non-linear research process but is rather, a cyclical
process. As the researcher develops questions and uncovers answers, more questions emerge and the
researcher must move through the steps again.

According to Spradley, following are the steps of conducting an ethnographic study (However, all
research topics may not follow all the steps listed here) :

1. Locating a social situation. The scope of the topic may vary from the “micro-ethnography” of a
“single-social-situation” to “macro-ethnography” of a complex society. According to Hymes, there
are three levels of ethnography including (i) “comprehensive ethnography” which documents an
entire culture, (ii) the “topic-oriented ethnography” which looks at aspects of a culture and (iii)
“hypothesis-oriented ethnography” which beings with an idea about why something happens in a
culture. Suppose you want to conduct research on classroom environment. This step requires that
you select a category of classroom environment and identify social and academic situations in
which it is used.

2. Collecting data. There are four types of data collection used in ethnographic research, namely, (a)
watching or being part of a social context using participant and non-participant observation and
noted in the form of on observer notes, logs, diaries, and so on, (b) asking open and closed
questions that cover identified topics using semi-structured interviews, (c) asking open questions
that enable a free development of conversation using unstructured interviews and (d) using
collected material such as published and unpublished documents, photographs, papers, videos and
assorted artefacts, letters, books or reports. The problem with such data is that the more you have,
greater is the effort required to analyse. Moreover, as the study progresses, the amount of data
increases making it more difficult and sharp to analyse the data. Yet more data leads to better codes,
categories, theories and conclusions. What is 'enough' data is subject to debate and may well be
constrained by the time and resource the researcher has available. Deciding when and where to
collect data can be a crucial decision. A profound analysis at one point may miss others, whilst a
broad encounter may miss critical finer points. Several deep dives can be a useful method. Social
data can be difficult to access due to ethics, confidentiality and determination necessary in such
research. There is often less division of activity phases in qualitative research and the researcher
may be memoing and coding as he proceeds with the study. The researcher usually uses theoretical
and selective sampling for data collection.

3. Doing participant observation. Formulate open questions about the social situations under study.
Malinowski opines that ethnographic research should begin with “foreshadowed problems”. These
problems are questions that researchers bring to a study and to which they keep an open eye but to
which they are not enslaved. Collect examples of the classroom environment. Select research
tools/techniques. Spradley provides a matrix of questions about cultural space, objects, acts
activities, events, time, actors, goals and feelings that researchers can use when just starting the
study.
4. Making an ethnographic record. Write descriptions of classroom environment and the situations in
which it is used.

5. Making descriptive observations. Select method for doing analysis.

6. Making domain analysis. Discover themes within the data and apply existing theories, if any, as
applicable. Domain analysis requires the researcher to first choose one semantic relationship such
as “causes” or “classes”. Second, you select a portion of your data and begin reading it and while
doing so, fill out a domain analysis worksheet where you list all the terms that fit the semantic
relationship you chose. Now formulate structural questions for each domain. Structural questions
 occur less frequently as compared to descriptive questions in normal conversation. Hence they
require more framing. Types of structural questions include the following :

(i) Verification and elicitation questions such as (a) verification of hypotheses (Is the teacher-
student relationship a conducive?), (b) domain verification (Are there different types of
teacher-student relationships? What are the different types? (c) verification of included terms
(is teachers’ strike an illegal activity?) and (d) verification of semantic relationship (Is teaching
beautiful?).

(ii) Frame substitution. This requires starting with real sentence like "you get a lot of brickbats in
administration". Then ask, can you think of any other terms that go in that sentence instead of
brickbats? You get a lot of _____ in administration. (This can be done systematically by
giving them list of terms to choose from).

(iii) Card sorts. Write phrases or words on cards. Then lay them out and ask the questions
mentioned above. The researcher can ask which words are similar. Testing hypotheses about
relations between domains and between domains and items. Like: "Are there different kinds of
classroom climates?" If yes, it is a domain. Then ask "what kinds of classroom climates are
there?” The final step in domain analysis is to make a list of all the hypothetical domains you
have identified, the relationships in these domain and the structural questions that follow your
analysis.

7. Making focussed observations.

8. Making a taxonomic analysis. Taxonomy is a scientific process of classifying things and arranging
them in groups or a set of categories (domains) organised on a single semantic relationships. The
researcher needs to test his taxonomies against data given by informants. Make comparisons of two
or three symbols such as word, event, constructs.

9. Making selected observations.

10. Making a componential analysis which is a systematic search fro the attributes or features of
cultural symbols that distinguish them from others and give them meaning. The basic idea in
componential analysis is that all items in a domain can be decomposed into combinations of
semantic features which combine to give the item meaning.

11. Discovering cultural themes. A theme is a postulate or position, explicit or implicit, which is
directly or indirectly approved and promoted in a society. Strategies of discovering cultural themes
include (i) in-depth study of culture, (ii) making a cultural inventory, (iii) identifying and analysing
components of all domains, (iv) searching for common elements across all domains such as gender,
age, SES groups etc., (v) identifying domains that clearly show a strong pattern of behaviour, (vi)
making schema of cultural scene and (vii) identifying generic (etic) codes usually functional such as
social conflict, inequality, cultural contradictions in the institutional social system, strategies of
social control, managing interpersonal relations, acquiring status in the institution and outside,
solving educational and administrative problems and so on.

12. Taking a cultural inventory.

13. Writing an ethnography

Guidelines for Interviewing

According to Patton, following are some useful guidelines that can be used for effective
interviewing :
1. Throughout all phases of interviewing, from planning through data collection to analysis, keep centred
on the purpose of the research endeavour. Let that purpose guide the interviewing process.
2. The fundamental principle of qualitative interviewing is to provide a framework within which
respondents can express their own understandings in their own terms.
3. Understand the strengths and weaknesses of different types of interviews: the informal conversational
interview; the interview guide approach; and the standardized open-ended interview.
4. Select the type of interview (or combination of types) that is most appropriate to the purposes of the
research effort.
5. Understand the different kinds of information one can collect through interviews: behavioural data;
opinions; feelings; knowledge; sensory data; and background information.
6. Think about and plan how these different kinds of questions can be most appropriately sequenced for
each interview topic, including past, present, and future questions.
7. Ask truly open-ended questions.
8. Ask clear questions, using understandable and appropriate language.
9. Ask one question at a time.
10. Use probes and follow-up questions to solicit depth and detail.
11. Communicate clearly what information is desired, why that information is important, and let the
interviewee know how the interview is progressing.
12. Listen attentively and respond appropriately to let the person know he or she is being heard.
13. Avoid leading questions.
14. Understand the difference between a depth interview and an interrogation. Qualitative evaluators
conduct depth interviews; police investigators and tax auditors conduct interrogations.
15. Establish personal rapport and a sense of mutual interest.
16. Maintain neutrality toward the specific content of responses. You are there to collect information not to
make judgments about that person.
17. Observe while interviewing. Be aware of and sensitive to how the person is affected by and responds to
different questions.
18. Maintain control of the interview.
19. Tape record whenever possible to capture full and exact quotations for analysis and reporting.
20. Take notes to capture and highlight major points as the interview progresses.
21. As soon as possible after the interview check the recording for malfunctions; review notes for clarity;
elaborate where necessary; and record observations.
22. Take whatever steps are appropriate and necessary to gather valid and reliable information.
23. Treat the person being interviewed with respect. Keep in mind that it is a privilege and responsibility to
peer into another person's experience.
24. Practice interviewing. Develop your skills.
25. Enjoy interviewing. Take the time along the way to stop and "hear" the roses.
 Writing Ethnographic Research Report

The components of an ethnographic research report should include the following :

1. Purpose / Goals / Questions.

2. Research Philosophy.
3. Conceptual/Theoretical Framework
4. Research Design / Model.
5. Setting/Circumstances.
6. Sampling Procedures.
7. Background and Experience of Researcher.
8. Role/s of Researcher.
9. Data Collection Method.
10. Data Analysis/Interpretation.
11. Applications/Recommendations.
12. Presentation Format and Sequence.

Advantages of Ethnography

These are as follows:

1. It provides the researcher with a much more comprehensive perspective than other forms of research
2. It is also appropriate to behaviours that are best understood by observing them within their natural
environment (dynamics)

Disadvantages of Ethnography

These are as follows:

1. It is highly dependent on the researcher’s observations and interpretations

2. There is no way to check the validity of the researcher’s conclusion, since numerical data is rarely
provided
3. Observer bias is almost impossible to eliminate
4. Generalizations are almost non-existent since only a single situation is observed, leaving ambiguity in
the study.
5. It is very time consuming.

Check Your Progress - IV

(a) State the characteristics of ethnographic research.

 
 

 
 

(b) Explain the steps of conducting ehtnographic research.

 
 

 
 

5.6 CASE STUDY:

Case study research is descriptive research that involves describing and interpreting events,
conditions, circumstances or situations that are occurring in the present. Case study seeks to engage with
and report the complexities of social activity in order to represent the meanings that individual social
actors bring to their social settings. It excels at bringing us to an understanding of a complex issue or
object and can extend experience or add strength to what is already known through previous research. Case
studies emphasize detailed contextual analysis of a limited number of events or conditions and their
relationships. Darwin's theory of evolution was based, in essence, on case study research, not
experimentation, for instance. In education, this is one of the most widely used qualitative approaches of
research.

According to Odum, “The case study method is a technique by which individual factor whether it
be an institution or just an episode in the life of an individual or a group is analyzed in its relationship to
any other in the group.” Its distinguishing characteristic is that each respondent is (individual, family,
classroom, institution, cultural group) is taken as a unit and the unitary nature of individual case is the
focus of analysis. It seeks to engage with and report the complexity of social and/or educational activity in
order to represent the meanings that individual actors in the situation bring to that setting. It assumes that
social and/or educational reality is created through social interactions, situated in specific contexts and
histories and seeks to identify and describe followed by analysing and theorising. It assumes that things
may not be as they seem and involve in-depth analysis so as to understand a ‘case’ rather than generalising
to a larger population. It derives much of its philosophical underpinnings and methodology from
ethnography, symbolic interactionism, ethnomethodology and phenomenology. It follows the ‘social
constructivism’ perspective of social sciences.
Most case studies are usually qualitative in nature. Case study research excels at enabling us to
understand a complex issue or object and can extend experience or add strength to what is already known
through previous research. Case studies involve a detailed contextual analysis of a limited number of
events or conditions and their relationships. Social scientists have made a wide use of this qualitative
research method to examine contemporary real-life situations and provide the basis for the application of
ideas and extension of methods. Yin defines the case study research method as an empirical inquiry that
investigates a contemporary phenomenon within its real-life context; when the boundaries between
phenomenon and context are not clearly evident; and in which multiple sources of evidence are used.
However, some case studies can also be quantitative in nature especially if they deal with cost-
effectiveness, cost-benefit analysis or institutional effectiveness. Many case studies have been done by
combining the qualitative as well as the quantitative approaches in which initially the qualitative approach
has been used and data have been collected using interviews and observations followed by the quantitative
approach. The approach of case studies ranges from general field studies to interview of a single individual
or group. A case study can be precisely focused on a topic or can include a broad view of life and society.
For example, a case study can focus on the life of a single gifted student, his actions, behaviour, abilities
and so on in his school or it can focus on the social life of an individual including his entire background,
experiences, motivations and aspirations that influence his behaviour society. Examples of case studies
include a ‘case’ of curriculum development, of innovative training, of disruptive behaviour, of an
ineffective institution and so on.
Case studies can be conducted to develop a ‘research-based’ theory with which to analyse
situations: a theory of, for and about practice. It is essential to note that since most case studies focus on a
single unit or small number of units, the findings cannot be generalised to larger populations. However, its
utility can not be underestimated. A case study is conducted with a fundamental assumption that though
human behaviour is situation-specific and individualised, there is a predictable uniformity in basic human
nature.
A case study can be conducted to explore, to describe or to explain a phenomenon. It could be a
synchronic study in which data are collected at one point of time or it could be longitudinal in nature. It
could be conducted at a single site or it could be multi-site. In other words, it is inherently a very flexible
methodology.

A case typically refers to a person, either a learner, a teacher, an administrator or an entity, such as a
school, a university, a classroom or a programme. In some policy-related research, the case could be a
country. Case studies may be included in larger quantitative or qualitative studies to provide a concrete
illustration of findings, or they may be conducted independently, either longitudinally or in a more
restricted temporal period. Unlike ethnographic research, case studies do not necessarily focus on cultural
aspects of a group or its members. Case study research may focus on a single case or multiple cases.

Characteristics of a Case Study

Following are the characteristics of a case study:

1. It is concerned with an exhaustive study of particular instances. A case is a particular instance of a

phenomenon. In education, examples of phenomena include educational programmes, curricula, roles,
events, interactions, policies, process, concept and so on. Its distinguishing feature is that each
respondent (individual, class, institution or cultural group) is treated as a unit.

2. It emphasises the study of interrelationship between different attributes of a unit.

3. According to Cooley, case study deepens our perception and gives us a clear insight into life… It gets
at behaviour directly and not by an indirect or abstract approach.

4. Each case study needs to have a clear focus which may include those aspects of the case on which the
data collection and analysis will concentrate. The focus of a study could be a specific topic, theme,
proposition or a working hypothesis.

5. It focuses on the natural history of the unit under study and its interaction with the social world around
it.

6. The progressive records of personal experience in a case study reveals the internal strivings, tensions
and motivations that lead to specific behaviours or actions of individuals or the unit of analysis.

7. In order to ensure that the case study is intensive and in-depth, data are collected over a long period of
time from a variety of sources including human and material and by using a variety of techniques such
as interviews and observations and tools such as questionnaires, documents, artefacts, diaries and so on.

8. According to Smith, as cited by Merriam, (1998), these studies are different from other forms of
qualitative of research in that they focus on a ‘single unit’ or a ‘bounded system’. A system is said to
be a bounded system if it includes a finite or limited number of cases to interviewed or observed within
a definite amount of time.
9. It may be defined as an in-depth study of one or more instances of a phenomenon- an individual, a
group, an institution, a classroom or an event- with the objective of discovering meaning, investigating
processes, gaining an insight and an understanding of an individual, group or phenomena within the
context in such a way that it reflects the real life context of the participants involved in the phenomena.
These individuals, groups, institutions, classrooms or events may represent the unit of analysis in a
case study. For example, in a case study, the unit of analysis may be a classroom and the researcher
may decide to investigate the events in three such classrooms.

10. According to Yin, case studies typically involve investigation of a phenomenon for which the
boundaries between the phenomenon and its context are not clearly evident. These boundaries should
be clearly clarified as part of the case study. He further emphasises the importance of conducting a case
study in its real life context. In education, the classroom or the school is the real life context of a case
study as the participants of such a case study are naturally found in these settings.

11. There are two major perspectives in a case study, namely, the etic perspective and the emic perspective.
The etic perspective is that of the researcher (i.e. the outsider’s perspective) whereas the emic
perspective is that of the research participants including teachers, principals and students (i.e. the
insider’s perspective). This enables the researcher to study the local, immediate meanings of social
actions of the participants and to study how they view the social situation of the setting and the
phenomenon under study. A comprehensive case study includes both the perspectives.

12. A case study can be a single-site study or a multi-site study.

13. Cases are selected on the basis of dimensions of a theory (pattern-matching) or on diversity on a
dependent phenomenon (explanation-building).

14. No generalization is made to a population beyond cases similar to those studied.

15. Conclusions are phrased in terms of model elimination, not model validation. Numerous alternative
theories may be consistent with data gathered from a case study.

16. Case study approaches have difficulty in terms of evaluation of low-probability causal paths in a model
as any given case selected for study may fail to display such a path, even when it exists in the larger
population of potential cases.

17. Acknowledging multiple realities in qualitative case studies, as is now commonly done, involves
discerning the various perspectives of the researcher, the case/participant, and others, which may or
may not converge.
Components of a Case Study Design
According to Yin, following are the five component elements of a case study design:
1. Study questions
2. Study propositions (if any are being used) or theoretical framework
3. Identification of the units of analysis
4. The logical linking of the data to the propositions (or theory)
5. The criteria for interpreting the findings.

The purpose of a case study is a detailed examination of a specific activity, event, institution, or
person/s. The hypotheses or the research questions are stated broadly at the beginning at the study. A
study’s questions are directed towards ‘how’ and ‘why’ considerations and enunciating and defining these
are the first task of the researcher. The study’s propositions could be derived from these ‘how’ and ‘why’
questions. These propositions could help in developing a theoretical focus. However, all case studies may
not have propositions. For instance, an exploratory case study may give only a purpose statement or
criteria that could guide the research process. The unit of analysis defines what the case study is focussing
on, whether an individual, a group, n institution, a city, a society, a nation and so on. Linkages between the
data and the propositions (or theory) and the criteria for interpreting the findings are usually the least
developed aspects of case studies (Yin, 1994).
Types of Case Study Designs
Yin (1994) and Winston (1997) have identified several types of case study designs. These are as
follows:
(A) Exploratory Case Study Design: In this type of case study design, field work and data collection
are carried out before determining the research questions. It examines a topic on which there is
very little prior research. Such a study is a prelude to a large social scientific study. However,
before conducting such an exploratory case study, its organisational framework is designed in
advance so as to ensure its usefulness as a pilot study of a larger, more comprehensive research.
The purpose of the exploratory study is to elaborate a concept, build up a model or advocate
propositions.

(B) Explanatory Case Study Design: These are useful when providing explanation to phenomena
under consideration. These explanations are patterns implying that one type of variation observed
in a case study is systematically related to another variation. Such a pattern can be a relational
pattern or a causal pattern depending on the conceptual framework of the study. In complex studies
of organisations and communities, multivariate cases are included so as to examine a plurality of
influences. Yin and Moore (1988) suggest the use of a pattern-matching technique in such a
research wherein several pieces of information from the same case may be related to some
theoretical proposition.

(C) Descriptive Case Study Design: A descriptive case study necessitates that the researcher present a
descriptive theory which establishes the overall framework for the investigator to follow
throughout the study. This type of case study requires formulation and identification of a
practicable theoretical framework before articulating research questions. It is also essential to
determine the unit of analysis before beginning the research study. In this type of case study, the
researcher attempts to portray a phenomenon and conceptualize it, including statements that
recreate a situation and context as much as possible.
(D) Evaluative Case Study Design : Often, in responsive evaluation, quasi-legal evaluation and
expertise-based evaluation, a case study is conducted to make judgments. This may include a deep
account of the phenomenon being evaluated and identification of most important and relevant
constructs, themes and patterns. Evaluative case studies can be conducted on educational
programmes funded by the Government such as “Sarva Shiksha Abhiyan” or Orientation
Programmes and Refresher Courses conducted by Academic Staff Colleges for college teachers or
other such programmes organised by the State and Local Governments for secondary and primary
school teachers.

Steps of Conducting a Case Study

Following are the steps of a case study:

1. Identifying a current topic which is of interest to the researcher.
2. Identifying research questions and developing hypotheses (if any).
3. Determining the unit of sampling and the number of units. Select the cases.
4. Identifying sources, tools and techniques of data collection. These could include interviews,
observations, documentation, student records and school databases. Collect data in the field.
5. Evaluating and Analysing Data.
6. Report writing.

Each of these is described in detail in the following paragraphs.

Step 1 : Identifying a current topic which is of interest to the researcher
In order to identify a topic for case study research, the following questions need to be asked:
(i) What kind of topics can be addressed using the case study method?
(ii) How can a case study research be designed, shaped and scoped in order to answer the research
question adequately?
(iii) How can the participation of individuals/institutions be obtained for the case study research?
(iv) How can case study data be obtained from case participants in an effective and efficient
manner?
(v) How can rigour be established in the case study research report so that it is publishable in
academic journals?
According to Maxwell, there are eight different factors that could influence the goals of a case study
as follows:

1. To grasp the meanings that events, situations, experiences and actions have for participants in the
study which is part of the reality that the researcher wants to understand.

2. To understand the particular context within which the participants are operating and its influence on
their actions, in addition to the context in which one’s research participants are embedded.
Qualitative researchers also take into account the contextual factors that influence the research
itself.

3. To identify unanticipated phenomena and influences that emerge in the setting and to generate new
grounded theories about such aspects.

4. To grasp the process by which events and actions take place that lead to particular outcomes.

5. To develop causal explanations based on process theory (which involves tracing the process by
which specific aspects affect other aspects), rather than variance theory (which involves showing a
relationship between two variables as in quantitative research).

6. To generate results and theories that are understandable and experientially credible, both to the
participants in the study and to others.

7. To conduct summative evaluations designed to improve practice rather than merely to assess the
value of a final programme or product.

8. To engage in collaborative and action research practitioners and research participants.

Step 2 : Identifying research questions and developing hypotheses (if any)

The second step in case study research is to establish a research focal point by forming questions
about the situation or problem to be studied and determining a purpose for the study. The research
objective in a case study is often a programme, an entity, a person or a group of people. Each objective is
likely to be connected to political, social, historical and personal issues providing extensive potential for
questions and adding intricacy to the case study. The researcher attains the objective of the case study
through an in-depth investigation using a variety of data gathering methods to generate substantiation that
leads to understanding of the case and answers the research questions. Case study research is usually
aimed at answering one or more questions which begin with "how" or "why." The questions are concerned
with a limited number of events or conditions and their inter-relationships. In order to formulate research
questions, literature review needs to be undertaken so as to establish what research has been previously
conducted. This helps in refining the research questions and making them more insightful. The literature
review, definition of the purpose of the case study and early determination of the significance of the study
for potential audience for the final report direct how the study will be designed, conducted and publicly
reported.

Step 3 : Determining the unit of sampling and the number of units. Select the cases.
Sampling Strategies in a Case Study : In a case study design, purposeful sampling is done which has
been defined by Patton as “selecting information-rich cases for study in-depth.” a case study research,
purposeful sampling is preferred over probability sampling as they enhance the usefulness of the
information acquired from small samples. Purposive samples are expected to be conversant and
informative about the phenomenon under investigation.
A case study requires a plan for choosing sites and participants in order to start data collection. The
plan is known as an ‘emergent design’ in which research decisions depend on preceding information. This
necessitates purposive sampling, data collection and partial, simultaneous analysis of data as well as
interactive rather than distinct sequential steps.

During the phase of designing a case study research, the researcher determines whether to use single
or multiple real-life cases to examine in-depth and which instruments and data collection techniques to
use. When multiple cases are used, each case is treated as a single case. Each case/s conclusions can then
be used as contributing information to the entire study, but each case remains a single case for collecting
data and analysis. Exemplary case studies carefully select cases and carefully examine the choices
available from among many research tools available so as to enhance the validity of the study. Careful
selection helps in determining boundaries around the case. The researcher must determine whether to study
‘unique cases’, or ‘typical cases’. He also needs to decide whether to select cases from different
geographical areas. It is necessary at this stage to keep in mind the goals of the study so as to identify and
select relevant cases and evidence that will fulfil the goals of the study and answer the research questions
raised. Selecting multiple or single cases is a key element, but a case study can include more than one unit
of embedded analysis. For example, a case study may involve study of a single type of school (Fro
example, Municipal School) and a school belonging to this type. This type of case study involves two
levels of analysis and increases the complexity and amount of data to be gathered and analyzed. Multiple
cases are often preferable to single cases, particularly when the cases may not be representative of the
population from which they are drawn and when a range of behaviours/profiles, experiences, outcomes, or
situations is desirable. However, including multiple cases limits the depth with which each case may be
analyzed and also has implications for the structure and length of the final report.

Step 4 : Identifying sources, tools and techniques of data collection

Sources of Data in a Case Study : A case study method involves using multiple sources and techniques
in the data collection process. The researcher determines in advance what evidence to collect and which
techniques of data analysis to use so as to answer the research questions. Data collected is normally
principally qualitative and soft data, but it may also be quantitative also. Data are collected from primary
documents such as school records and databases, students’ records, transcripts and results, field notes, self-
reports or think-aloud protocols and memoranda. Techniques used to collect data can include surveys,
interviews, questionnaires, documentation review, observation and physical artefacts. These multiple tools
and techniques of data collection add texture, depth, and multiple insights to an analysis and can enhance
the validity or credibility of the results.

Case studies may make use of field notes and databases to categorize and reference data so that it is
readily available for subsequent re-interpretation. Field notes record feelings and intuitive hunches, pose
questions, and document the work in progress. They record testimonies, stories and illustrations which can
be used in reporting the study. They may inform of impending preconceptions because of the detailed
exposure of the client to special attention or give an early signal that a pattern is emerging. They assist in
determining whether or not the investigation needs to be reformulated or redefined based on what is being
observed. Field notes should be kept separate from the data being collected and stored for analysis.

According to Cohen and Manion, the researcher must use the chosen data collection tools and
techniques systematically and properly in collecting the evidence. Observations and data collection
settings may range from natural to artificial, with relatively unstructured to highly structured elicitation
tasks and category systems depending on the purpose of the study and the disciplinary traditions associated
with it.

Case studies necessitate that effective training programmes be developed for investigators, clear
protocols and procedures be established in advance before starting the field work and conduct a pilot study
in before moving into the field so as to eliminate apparent obstacles and problems. The researcher training
programme need to cover the vital concepts of the study, terminology, processes and methods and need to
teach researcher/s how to apply the techniques being used in the study accurately. The programme should
also be aimed at training researcher/s to understand how the collection of data using multiple techniques
strengthens the study by providing opportunities for triangulation during the analysis phase of the study.
The programme should also include protocols for case study research including time deadlines, formats for
narrative reporting and field notes, guidelines for collection of documents, and guidelines for field
procedures to be used. Investigators need to be good listeners who can hear exactly the words being used
by those interviewed. Qualities of effective investigators also include being able to ask good questions and
interpret answers. Effective investigators not only review documents looking for facts but also read
between the lines and pursue collaborative evidence elsewhere when that seems appropriate. Investigators
need to be flexible in real-life situations and not feel threatened by unexpected change, missed
appointments or lack of space. Investigators need to understand the goals of the study and comprehend the
issues and must be open to contrary findings. Investigators must also be aware that they are going into the
world of real human beings who may be threatened or unsure of what the case study will bring.

After investigators are trained, the final advance preparation step is to select a site for pilot study
and conduct a pilot test using all the data collection tools and techniques so that difficult and tricky areas
can be uncovered and corrected. Researchers need to anticipate key problems and events, identify key
people, prepare letters of introduction, establish rules for confidentiality, and actively seek opportunities to
revisit and revise the research design in order to address and add to the original set of research questions.

Throughout the design phase, researchers must ensure that the construct validity, internal validity,
external validity, and reliability of the tools and the research method are adequate. Construct validity
requires the researcher to use the suitable measures for the concepts being studied. Internal validity
(especially important in explanatory or causal studies) demonstrates that certain conditions/events (causes)
lead to other conditions/events (effect/s) and necessitates the use of multiple sets of evidence from multiple
sources to reveal convergent lines of inquiry. The researcher makes efforts to ascertain a series of
substantiation forward and backward. External validity reflects whether findings are generalisable beyond
the immediate case/s. The more variations in places, people and procedures a case study can withstand and
still yield the same findings, the more will be its external validity. Techniques such as cross-case
examination and within-case examination along with literature review help in ensuring external validity.
Reliability refers to the stability, accuracy and precision of measurement. Exemplary case study design
ensures that the procedures used are well documented and can be repeated with the same results over and
over again. Establishing a trusting relationship with research participants, using multiple data collection
procedures, obtaining sufficient pertinent background information about case participants and sites and
having access to or contact with the case over a period of time are, in general, all decidedly advantageous.

Step 5 : Evaluating and analysing data

The case study research generates a huge quantity of data from multiple sources. Hence systematic
organisation of the data is essential in prevent the researcher from losing sight of the original research
purpose and questions. Advance preparation assists in handling huge quantity of largely soft data in a
documented and systematic manner. Researchers prepare databases for categorizing, sorting, storing and
retrieving data for analysis. The researcher examines raw data so as to find linkages between the research
object and the outcomes with reference to the original research questions. Throughout the evaluation and
analysis process, the researcher remains open to new opportunities and insights. The case study method,
with its use of multiple data collection methods and analysis techniques, provides researchers with
opportunities to triangulate data in order to strengthen the research findings and conclusions. According to
Creswell, analysis of data in case study research usually involves an iterative, spiralling or cyclical process
that proceeds from more general to more specific observations. According to Miles and Huberman, data
analysis may commence during interviews or observations and continue during transcription, when
recurring themes, patterns and categories become apparent. Once written records are available, analysis
involves the coding of data and the identification of prominent points or structures. Having additional
coders is highly desirable, especially in structural analyses of discourse, texts, syntactic structures or
interaction patterns involving high-inference categories leading ultimately to the quantification of types of
items within categories. Data reduction may include quantification or other means of data aggregation and
reduction, including the use of data matrices, tables, and figures.

The strategies used in analysis require researchers to move beyond initial impressions to improve
the likelihood of precise and consistent findings. Data need to be consciously sorted in many different
ways to expose or create new insights and will deliberately look for contradictory data to disconfirm the
analysis. Researchers categorize, tabulate and recombine data to answer the initial research questions and
conduct cross-checking of facts and incongruities in accounts. Focused, short, repeated interviews may be
essential to collect supplementary data to authenticate key observations or check a fact.

Precise techniques that could be used for data analysis include placing information into arrays,
creating matrices of categories, creating flow charts or other displays and tabulating frequency of events.
Researchers can use quantitative data to substantiate and support the qualitative data so as to comprehend
the raison d'être or theory underlying relationships. Besides, multiple investigators could be used to gain
the advantage provided when diverse perspectives and insights scrutinize the data and the patterns. When
the multiple observations converge, reliability of the findings enhances. Inconsistent discernments, on the
other hand, necessitate the researchers to inquire more intensely. Moreover, the cross-case search for
patterns, keeps investigators from reaching untimely conclusions by requiring that investigators look at the
data in diverse ways. Cross-case analysis divides the data by type across all cases investigated. One
researcher then examines the data of that type carefully. When a pattern from one data type is substantiated
by the evidence from another, the result is stronger. When substantiation conflicts, deeper probing of the
variation is necessary to identify the cause/s or source/s of conflict. In all cases, the researcher treats the
evidence reasonably to construct analytic conclusions answering the original "how" and "why" research
questions.

Step 6 : Report writing

Case studies report the data in a way that transforms a multifarious issue into one that can be
understood, permitting the reader to question and examine the study and reach an understanding
independent of the researcher. The objective of the written report is to depict a multifaceted problem in a
way that conveys an explicit experience to the reader. Case studies should present data in a way that leads
the reader to apply the experience in his or her own real-life situation. Researchers need to pay exacting
consideration to displaying adequate evidence to achieve the reader’s confidence that all avenues have
been explored, clearly communicating the confines of the case and giving special attention to conflicting
propositions.

In general, a research report in a case study should include the following aspects:

• A statement of the study's purpose and the theoretical context.

• The problem or issue being addressed.
• Central research questions.
• A detailed description of the case(s) and explanation of decisions related to sampling and selection.
• Context of the study and case history, where relevant. The research report should provide sufficient
contextual information about the case, including relevant biographical and social information
(depending on the focus), such as teaching - learning history, students’ and teachers’ background,
years of studying/working in the institution, data collection site(s) or other relevant descriptive
information pertaining to the case and situation.
• Issues of access to the site/participants and the relationship between you and the research participant
(case).
• The duration of the study.
• Evidence that you obtained informed consent, that the participants' identities and privacy are
protected, and, ideally, that participants benefited in some way from taking part in the study.
• Methods of data collection and analysis, either manual or computer-based data management and
analysis (see weitzman & miles, 1995), or other equipment and procedures used.
• Findings, which may take the form of major emergent themes, developmental stages, or an in-depth
discussion of each case in relation to the research questions; and illustrative quotations or excerpts
and sufficient amounts of other data to establish the validity and credibility of the analysis and
interpretations.
• A discussion of factors that might have influenced the interpretation of data in undesired,
unanticipated, or conflicting ways.
 A consideration of the connection between the case study and larger theoretical and practical issues
in the field is essential to report. The report could include a separate chapter handling each case separately
or treating the case as a chronological recounting. Some researchers report the case study as a story.
During the report preparation process, the researcher critically scrutinizes the report trying to identify ways
of making it comprehensive and complete. The researcher could use representative audience groups to
review and comment on the draft report. Based on the comments, the researcher could rewrite and revise
the report. Some case study researchers suggest that the report review audience should include the
participants of the study.

Strengths of Case Study Method

1. It involves detailed, holistic investigation of all aspects of the unit under study.
2. Case studies data are strong in reality.
3. It can utilise a wide range of measurement tools and techniques.
4. Data can be collected over a period of time and is contextual.
5. It enables the researcher to assess and document not just the empirical data but also how the subject
or institution under study interacts with the larger social system.
6. Case study reports are often written in non-technical language and are therefore easily understood
by laypersons.
7. They help in interpreting similar other cases.

Weaknesses of Case Study Method

1. The small sample size prevents the researcher from generalising to larger populations.
2. The case study method has been criticised for use of a small number of cases can offer no
grounds for establishing reliability or generality of findings.
3. The intense exposure to study of the case biases the findings.
4. It has also been criticised as being useful only as an exploratory tool.
5. They are often not easy to cross-check.

Yet researchers continue to use the case study research method with success in carefully
planned and crafted studies of real-life situations, issues, and problems.

Check Your Progress - V

(a) State the meaning of case study research.

 
 

 
 

(b) Explain the characteristics of case study research.

 
 

 
 (c) Explain the steps of case study research.
 
 

5.7 ANALYTICAL METHOD:

It involves the identification and interpretation of data already existing in documents, pictures and
artefacts. It is a form of research in which events, ideas, concepts or artefacts are examined through
analysis of documents, records, recordings or other media. Here, contextual information is very essential to
for an accurate interpretation of data. Historical research comprises of systematic collection and analysis of
documents, records and artefacts with the objective of providing a description and interpretation of past
events or persons. Its application lies in a range of research methods such as historical research which
could use both quantitative and qualitative data, legal analysis which focuses on selected laws and court
decisions with the objective of understanding how legal principles and precedents apply to educational
practices, concept analysis which is carried out to understand the meaning and usage of educational
concepts (eg. school-based reforms, ability grouping, affective teacher education) and content analysis
which is carried out to understand the meaning and identify properties of large amounts of textual
information in a systematic manner.
Characteristics of Analytical Research

Following are the characteristics of analytical research:

1. It does not ‘create’ or ‘generate’ data through research tools and techniques.
2. The topic of analytical research deals with the past.
3. It reinterprets existing data.
4. It predominantly uses primary sources for collecting data.
5. Internal and external criticism is used as a technique while searching for facts and providing
interpretative explanations.
6. It uses documents, relics and oral testimonies for collecting data.
Objectives Analytical Research

Following are the objectives of analytical research:

1. It offers understanding of the past/existing/available data.

2. It enables the researcher to shed light on existing policies by interpreting the past.
3. It generates a sense of universal justification and underlying principles and aims of education in a
society.
4. It reinterprets the past for each age group.
5. It uses data and logic to analyse the past and demythologises idealised conceptions of the past.

Check Your Progress - VI

(a) State the meaning of analytical research.

 
 
 

Suggested Readings

Auberbach, C. F. and Silverstein, L. B. Qualitative Data: An Introduction to Coding and Analysis. New
York: New York University Press. 2003.

Baron, R. A. Psychology. India : Allyn and Bacon. 2001.

Brewer, M. (2000). Research Design and Issues of Validity. In Reis, H. & Judd, C. (eds) Handbook of
Research Methods in Social and Personality Psychology. Cambridge:Cambridge University
Press.
Cohen, L and Manion, L. Research Methods in Education. London :
Routledge, 1989.

Creswell, J. W. Educational Research, Planning, Conducting, and Evaluating Quantitative and Qualitative
Research, University of Netvaska : Merrill Prentice Hall, 2002,

Creswell, J. W. Qualitative Inquiry and Research Design: Choosing among Five Traditions. Sage
Publications, Inc. 1998.

Picciano, A. G. Educational Research Primer. London : Continuum. 2004.

 6
 

HISTORICAL RESEARCH 
 
 

Unit Structure: 

6.0  Objectives 

6.1  Introduction 

6.2  Meaning 

6.3  The purpose of Historical Research 

6.4  Characteristics of Historical Research 

6.5  Scope of Historical Research in Education 

6.6  Approaches to the study of History 

6.7  Steps in Historical Research 

6.8  Problems and Weaknesses to be avoided in Historical Research. 

6.9  Criteria of Evaluating Historical Research. 

6.0 OBJECTIVES: 

After reading this unit the student will be able to: 

• Define the meaning of historical research, its purposesnad characteristics, scope and approaches to 
the study of history. 
• Explain the steps of historical research. 
• State the Weaknesses to be avoided in Historical Research. 
 

6.1 INTRODUCTION : 
 

  History usually refers simply to an account of the past of human societies. It is the study of what 
“can be known…(to the historian)… through the surviving record.” Gottschalk referred to this as ‘history 
as  record’,  He  further  stated  that  “The  process  of  critically  examining  and  analyzing  the  records  and 
survivals of the past is … called historical method. The imaginative reconstruction of the past from the 
data derived by that process is called historiography (the writing of history)”. 

6.2 MEANING : 

  Historical  research  has  been  defined  as  the  systematic  and  objective  location,  evaluation  and 
synthesis  of  evidence  in  order  to  establish  facts  and  draw  conclusions  about  past  events.  It  involves  a 
critical inquiry of a previous age with the aim of reconstructing a faithful representation of the past. In 
historical research, the investigator studies documents and other sources that contain facts concerning 
the  research  theme  with  the  objective  of  achieving  better  understanding  of  present  policies,  practices, 
problems  and  institutions.  An  attempt  is  made  to  examine  past  events  or  combinations  of  events  and 
establish facts in order to arrive at conclusions concerning past events or predict future events. Historical 
research is a type of analytical research. Its common methodological characteristics include (i) identifying 
a  research  topic  that  addresses  past  events,  (ii)  review  of  primary  and  secondary  data,  (iii)  systematic 
collection  and  objective  evaluation  of  data  related  to  past  occurrences  with  the  help  of  techniques  of 
criticism for historical searches and evaluation of the information and (iv) synthesis and explanation of 
findings in order to test hypotheses concerning causes, effects or trends of these events that may help to 
explain  present  events  and  anticipate  future  events.  Historical  studies  attempt  to  provide  information 
and  understanding  of  past  historical,  legal  and  policy  events.  The  historical  method  consists  of  the 
techniques and guidelines by which historians use historical sources and other evidences to research and 
then to write history. 

  

6.3 THE PURPOSE OF HISTORICAL RESEARCH : 

  Conducting historical research in education can serve several purposes as follows:  

1.   It enables educationists to find out solutions to contemporary problems which have their roots in the 
past.  i.e.  it  serves  the  purpose  of  bringing  about  reforms  in  education.  The  work  of  a  historical 
researcher  sometimes  sensitizes  educators  to  unjust  or  misguided  practices  in  the  past  which  may 
have unknowingly continued into the present and require reform. A historical researcher studies the 
past with a detached perspective and without any ego‐involvement with the past practices. Hence it 
 could  be  easier  for  educationists  to  identify  misguided  practices  thus  enabling  them  to  bring  about 
reforms. 

2.   It throws light on present trends and can help in predicting future trends. If we understand how an 
educationist or a group of educationists acted in the past, we can predict how they will act in future. 
Similarly, studying the past enables a researcher to understand the factors / causes affecting present 
trends.  In  order  to  make  such  future  predictions  reliable  and  trustworthy,  the  historical  researcher 
needs  to  identify  and  clearly  describe  in  which  ways  the  past  differs  from  the  present  context  and 
how  the  present  social,  economic  and  political  situations  and  policies  could  have  an  impact  on  the 
present and the future. 

3.  It  enables  a  researcher  to  re‐evaluate  data  in  relation  to  selected  hypotheses,  theories  and 
generalizations that are presently held about the past. 

4.  It emphasizes and analyzes the relative importance and the effect of the various interactions in the 
prevailing cultures. 

5.  It enables us to understand how and why educational theories and practices developed. 

6.4 CHARACTERISTICS OF HISTORICAL RESEARCH 

These are as follows:  

1. It is not a mere accumulation of facts and data or even a portrayal of past events.  
2. It is a flowing, vibrant report of past events which involves an analysis and explanation of these 
occurrences with the objective of recapturing the nuances, personalities and ideas that influenced 
these events.  
3. Conducting historical research involves the process of collecting and reading the research material 
collected and writing the manuscript from the data collected. The researcher often goes back‐and‐
forth between collecting, reading, and writing. i.e. the process of data collection and analysis are 
done simultaneously are not two distinct phases of research. 
4. It  deals  with  discovery  of  data  that  already  exists  and  does  not  involve  creation  of  data  using 
structured tools. 
5. It is analytical in that it uses logical induction.  
6. It has a variety of foci such as issues, events, movements and concepts. 
7. It records and evaluates the accomplishments of individuals, agencies or institutions 
 
6.5 SCOPE OF HISTORICAL RESEARCH IN EDUCATION 

1.  General educational history of specific periods such as (a) ancient India, (b) A during British rule, (c) 
Independent India etc. 
2.  History  of  specific  levels  of  education  (a)  primary  education,                            (b)  secondary  education,  (c) 
tertiary education etc. in India. 
3.  History  of  specific  types  of  education  such  as  (a)  adult  education,    (b)  distance  education,  (c) 
disadvantaged education, (d) women’s education in India. 
4.  Historical study of specific educational institutions such as (i) University of Mumbai, (ii) Aligarh Muslim 
University and so on. 
5.  History of the role of the teacher in ancient India. 
6.  History  of  specific  components  of  education  such  as  (a)  curriculum,  (b)  text‐books,  (c)  teaching‐
learning  methods,  (d)  aims  and  objectives  of  education,  (e)  teacher‐student  relationships,  (f) 
evaluation process and so on. 
7.  History of national education policies in India. 
8.  History  of  admission  processes  in  professional  /  technical  courses  (medicine,  engineering, 
management) in India. 
9.  History of teacher education. 
10. Historical biographies of major contributors to education such as Mahatma Gandhi, Maharshi Karve, 
Maharshi Phule, Shri Aurobindo, Gurudev Tagore and so on. 
11. History of educational administration. 
12. History of public financing of education. 
13. History of educational legislation in India. 
14. History of educational planning. 
15. History of contemporary problems in India. 
16. Historical study of the relationship between politics and education in India. 
17. Historical study of the impact of the British rule in India. 
18. Comparative history of education in India and some other country / countries. 
19. Historical study of the system of state‐sponsored inspection in India. 
20. Historical  study  of  education  in  specific  Indian  states  such  as  Maharashtra,  Tamil  Nadu,  Madhya 
Pradesh, Rajasthan etc. 
 

  In other words, historical research in education may be concerned with an individual, a group, an 
idea a movement or an institution. 

 
  If a historical study focuses on an entire country / society / system, i.e. if it is broad in scope, it is 
said  to  be  a  macro‐level  historical  research.  On  the  other  hand,  if  its  focus  is  narrow  and  includes  a 
selective set of people or events of interest, it is said to be a micro‐level historical research. 

6.6 APPROACHES TO THE STUDY OF HISTORY: 

According to Monaghan and Hartman, there are four major approaches to the study of the past:

a. Qualitative Approach : This is what most laypersons think of as history: the search for a story inferred
from a range of written or printed evidence. The resultant history is organised chronologically and
presented as a factual tale: a tale of a person who created reading textbooks, such as a biography of
William Holmes McGuffey (Sullivan, 1994) or the Lindley Murray family (Monaghan, 1998) in the
Western context. The sources of qualitative history range from manuscripts such as account books,
school records, marginalia, letters, diaries and memoirs to imprints such as textbooks, children’s books,
journals, and other books of the period under consideration.

b. Quantitative Approach : Here, rather than relying on “history by quotation,” as the former approach
has been negatively called, researchers intentionally look for evidence that lends itself to being counted
and that is therefore presumed to have superior validity and generalisability. Researchers have sought
to estimate the popularity of a particular textbook by tabulating the numbers printed, based on
copyright records. The assumption is that broader questions such as the relationship between education
and political system in India or between textbooks and their influence on children can thus be
addressed more authoritatively.

c. Content Analysis : Here the text itself is the focus of examination. This approach uses published works
as its data (in the case of history of textbooks, these might be readers, or examples of the changing
contents of school textbooks in successive editions) and subjects them to a careful analysis that usually
includes both quantitative and qualitative aspects. Content analysis has been particularly useful in
investigating constructs such as race, caste, etc.

d. Oral History : Qualitative, quantitative, and content approaches use written or printed text as their
database. In contrast, the fourth approach, oral history, turns to living memory. For instance, oral
historians interested in women’s education could ask their respondents about their early experiences
and efforts in women’s education.

These four approaches are not, of course, mutually exclusive. Indeed, historians avail themselves of
as many of these as their question, topic, and time period permit. This integration is possible because the
nature of historical research cuts across a variety of approaches, all of which commence with the
recognition of a topic and the framing of a question. In other words, a historical study may be quantitative
in nature, qualitative in nature or a combination of the approaches.

  Its  purpose  can  be  mainly  descriptive,  aiming  to  understand  some  specific  development  in  a 
particular  period  of  time  in  a  particular  culture;  or  it  could  be  explanatory,  trying  to  test  and  accept  / 
reject widely held assumptions. 
 

  A historical investigation is conducted with objectivity and the desire to minimize bias, distortion 
and  prejudice.  Thus,  it  is  similar  to  descriptive  method  of  research  in  this  aspect.  Besides,  it  aims  at 
describing all aspects of the particular situation under study (or all that is accessible) in its search for the 
truth. Thus, it is holistic, comprehensive in nature and is similar to the interpretive approach. Though it is 
not  empirical  in  nature  (does  not  collect  data  through  direct  observation  or  experimentation),  it  does 
make use of reports (all the available written and/or oral material), it definitely qualifies to be a scientific 
activity.  This  is  because  it  requires  scholarship  to  conduct  a  systematic  and  objective  study  and 
evaluation and synthesis of evidence so as to arrive at conclusions. In other words, historical research is 
scientific in nature. 

  Moreover,  any  competent  researcher  in  other  types  of  empirical  studies  reviews  the  related 
literature so as to find out prior researches and theoretical work done on a particular topic. This requires 
studying journals, books, encyclopedias, unpublished theses and so on. This is followed by interpretation 
of their significance. These steps are common to empirical research and historical research. i.e. to some 
extent, every researcher makes use of the historical method in his/her research. 

  However, it should be mentioned here that historical researcher in education “discovers” already 
existing data from a wide range of historical sources such as documents, relics, autobiographies, diaries 
or photographs. On the other hand, in other types of educational studies, the researcher “creates” data 
through  observations,  measurement  through  tests  and  experimentation.  To  this  extent,  historical 
research differs from descriptive and experimental researches. 

Check Your Progress ‐ I 

Q.1   Define the following 

    (a)  Characteristics of historical research in education. 

    (b)  Purposes of historical research. 

Q.2  (a) Give examples of research topics in historical    research  

          (b)  Explain the approaches to historical research.  
     

6.7 STEPS IN HISTORICAL RESEARCH : 

  The essential steps involved in conducting a historical research are as follows: 

A. Identify a topic/subject and define the problems/questions to be investigated. 
B. Search for sources of data. 
C. Evaluate the historical sources. 
D. Analyze, synthesize and summarize interpreting the data  / information.  
E. Write the research report. 
 

  Since  most  historical  studies  are  largely  qualitative  in  nature,  the  search  for  sources  of  data, 
evaluating,  analyzing,  synthesizing  and  summarizing  information  and  interpreting  the  findings  may  not 
always be discreet, separate, sequential steps i.e. the sequence of steps in historical research is flexible.  

  Let us now look at each of these steps in details. 

A. Identify a Topic and Define the Problem 
 

    According  to  Borg,  “In  historical  research,  it  is  especially  important  that  the  student  carefully 
defines  his  problem  and  appraises  its  appropriateness  before  committing  himself  too  fully.  Many 
problems are not adaptable to historical research methods and cannot be adequately treated using this 
approach. Other problems have little or no chance of producing significant results either because of the 
lack of pertinent data or because the problem is a trivial one.” 

  Beach has classified the problems that prompt historical inquiry into five types: 
 

1.  Current  social  issues  are  the  most  popular  source  of  historical  problems  in  education.  e.g.  Rural 
education, adult and continuing education, positive discrimination in  education etc. 

2.  Histories  of  specific  individuals,  histories  of  specific  educational  institutions  and  histories  of 
educational  movement.  These  studies  are  often  conducted  with  “the  simple  desire  to  acquire 
knowledge about previously unexamined phenomena”.  

3.  A historical study of interpreting ideas or events that previously had seemed unrelated. For example, 
history  of  educational  financing  and  history  of  aims  of  education  in  India  may  be  unrelated.  But  a 
person  reviewing  these  two  researches  separately  may  detect  some  relationship  between  the  two 
histories and design a study to understand this relationship. 

4.  A historical study aimed at synthesizing old data or merge them with new historical facts discovered 
by the researcher. 

5.  A historical inquiry involving reinterpretation of past events that have been studied by other historical 
researchers. This is known as revisionist history. 

  On  the  other  hand,  in  order  to  identify  a  significant  research  problem,  Gottschalk    recommends 
that four questions should be asked:  

  (i) Where do the events take place? 
  (ii) Who are the persons involved? 
  (iii) When do the events occur? 
  (iv) What kinds of human activity are involved? 
  The scope of the study can be determined on the basis of the extent of emphasis placed on the 
four  questions  identified  by  Gottschalk  i.e.  the  geographical  area  included,  the  number  of  persons 
involved, the time span included and the number and kinds of human activities involved often, the exact 
scope  and  delimitation  of  a  study  is  decided  by  a  researcher  only  after  the  relevant  material  has  been 
obtained.  The  selection  of  a  topic  in  historical  research  depends  on  several  personal  factors  of  the 
researcher  such  as  his/her  motivation,  interest,  historical  knowledge  and  curiosity,  ability  to  interpret 
historical  facts  and  so  on.  If  the  problem  selected  involves  understanding  an  event,  an  institution,  a 
person, a past period, more clearly, it should be taken up for a research. 
 
  The  topic  selected  should  be  defined  in  terms  of  the  types  of  written  materials  and  other 
resources available to you.  
 
   This should be followed by formulating a specific and testable hypothesis or a series of research 
questions,  if  required.  This  will  provide  a  clear  focus  and  direction  to  data  collection,  analysis  and 
interpretation. i.e. it provides a structure to the study.  
 
  According  to  Borg,  without  hypotheses,  historical  research  often  becomes  little  more  than  an 
aimless gathering of facts.  
 
B. Search for Sources of Data 
 
  Historical  research  is  not  empirical  in  that  it  does  not  include  direct  observation  of  events  or 
persons.  Here,  the  researcher  interprets  past  events  on  the  basis  of  traces  they  have  left.  He  uses  the 
evidence of past acts and thoughts. Thus, through he/she does not use his/her own observation but on 
other people’s observations. The researcher’s job here is to test the truthfulness of the reports of other 
people’s  observations.  These  observations  are  obtained  from  several  sources  of  historical  data.  Let  us 
now try to discuss various sources of historical data. 
 
Sources of Historical Data 
 
  These sources are broadly classified into two types: 
 
(a) Primary Sources: Gottschalk defines a primary data source as “the testimony of any eyewitness, or of 
a witness by any other of the senses, or of a mechanical device like the Dictaphone – that is, of one who 
…  was  present  at  the  events  of  which  he  tells.  A  primary  source  must  thus  have  been  produced  by  a 
contemporary  of  the  events  it  narrates.”  In  other  words,  primary  sources  are  tangible  materials  that 
provide a description of an historical event and were produced shortly after the event happened. They 
have a direct physical relationship to the event being studied. Examples of primary sources include new 
paper report, letters, public documents, court decisions, personal diaries, autobiographies, artifacts and 
eyewitness’s verbal accounts. These primary sources of data can be divided into two broad categories as 
follows:   
 
(i) The remains or relics of a given historical period. These could include photographs, coins, skeletons, 
fossils, tools, weapons, utensils, furniture, buildings and pieces of art and culture (object d’ art). Though 
these were not originally meant for transmitting information to future generations they could prove very 
useful sources in providing reliable and sound evidence about the past. Most of these relics provide non‐
verbal information. 
 
(ii)  Those  objects  that  have  a  direct  physical  relationship  with  the  events  being  reconstructed.  This 
includes  documents  such  as  laws,  files,  letters,  manuscripts,  government  resolutions,  charters, 
memoranda,  wills,  news‐papers,  magazines,  journals,  films,  government  or  other  official  publications, 
maps,  charts,  log‐books,  catalogues,  research  reports,  record  of  minutes  of  meetings,  recording, 
inscriptions, transcriptions and so on. 
 
 (b)  Secondary Sources: A secondary source is one in which the eyewitness or the participant i.e. the 
person describing the event was not actually present but who obtained his/her descriptions or narrations 
from  another  person  or  source.  This  another  person  may  or  may  not  be  a  primary  source.  Secondary 
sources, thus, do not have a direct physical relationship with the event being studies. They include data 
which  are  not  original.  Examples  of  secondary  sources  include  textbooks,  biographies,  encyclopedias, 
reference  books,  replicas  of  art  objects  and  paintings  and  so  on.  It  is  possible  that  secondary  sources 
contain  errors  due  to  passing  of  information  from  one  source  to  another.  These  errors  could  get 
multiplied  when  the  information  passes  through  many  sources  thereby  resulting  in  an  error  of  freat 
magnitude in the final data. Thus, wherever possible, the researcher should try to use primary sources of 
data. However, that does not reduce the value of secondary sources. 
 

  In  conclusion,  the  various  sources  of  historical  information‐both  primary  and  secondary  can  be 
summarized as follows:   
 
  Sources of Historical Information 

   

   

  Documents    Quantitative    Oral Records    Relics 

  (written / printed)  Records   (Spoken words) (Physical or   

                                                                                                              Visual objects) 

  ‐ diaries   ‐ School budgets  ‐ Ballads    ‐ School Buildings 

  ‐ memoirs    ‐ Student attendance   ‐ Tales      ‐ School Furniture 

  ‐ notebooks       records    ‐ Saga      ‐ Textbooks 

  It must be mentioned here that the branch of historical research using all or some types of oral 
records is known as oral history. 

  It  should  also  be  mentioned  here  that  some  objects  can  be  classified  as  documents  or  relics 
depending  on  the  how  they  are  used  in  a  historical  study.  For  example,  in  a  research  study  on  how  a 
historical figure (a politician, a freedom fighter or a social reformer) is presented in textbooks of different 
periods, the textbook will be classified as a document as the emphasis here is on analyzing its content‐
matter given in a verbal form. On the other hand, in a research study on printing methods in the past, the 
textbook  can  be  used  as  a  relic  as  the  focus  here  is  not  on  analyzing  its  contents  but  on  its  physical, 
outward characteristics or features. 

Searching for Historical Data 

  The  procedure  of  searching  for  historical  data  should  be  systematic  and  pre‐planned.  The 
researcher  should  know  what  information  he  needs  so  as  to  identify  important  sources  of  data  and 
provide a direction to his search for relevant data. Using his knowledge, imagination and resourcefulness, 
he needs to explore the kinds of data required, persons involved, institutions involved. This will help him 
to identify the kinds of records he require and whom he should interview. Since a historical research is 
mainly qualitative in nature all the primary and secondary sources cannot be identified in advance. It is 
possible that  as  one collects  some  data,  analyzes  and  interprets  it,  the  need for  further pertinent  data 
may  arise  depending  on  the  interpretive  framework.  This  will  enable  him  to  identify  other  primary  or 
secondary sources of data. 

  The search for sources of data begins with wide reading of preliminary sources including published 
bibliographies,  biographies,  atlas,  specialized  chronologies,  dictionaries  of  quotations  and  terms.  Good 
university and college libraries tend to have a great deal of such preliminary materials. This will enable a 
researcher  to  identify  valuable  secondary  sources  on  the  topic  being  studied  such  books  on  history 
relating  to  one’s  topic.  For  extensive  materials  on  a  subject,  the  researcher  may  need  to  go  to  a  large 
research library or a library with extensive holdings on a specific subject. Such secondary materials could 
include  other  historian’s  conclusions  and  interpretations,  historical  information,  references  to  other 
secondary  and  primary  sources.  The  historical  researcher  needs  to  evaluate  the  secondary  sources  for 
their  validity  and  authenticity.  Now  the  researcher  should  turn  his  attention  to  the  primary  sources. 
These  are  usually  available  in  the  institution  or  the  archives  especially  if  the  source  concerns  data 
pertaining  to  distant  past  or  data  pertaining  to  events  in  which  the  chief  witnesses  are  either  dead  or 
inaccessible.  In  case  of  data  concerning  the  recent  past,  the  researcher  can  contact  witnesses  or 
participants themselves in order to interview them and/or study the documents possessed by them.   

  However,  it  is  not  possible  for  a  historical  researcher  to  examine  all  the  material  available. 
Selecting  the  best  sources  of  data  is  important  in  a  historical  study.  In  a  historical  study  the  complete 
“population” of available data can never be obtained or known. Hence the sample of materials examined 
must always be a purposive one. What it represents and what it fails to represent should be considered. 
The  researcher  needs  to  identify  and  use  a  sample  that  should  be  representative  enough  for  wider 
generalization. 
c) Evaluation of the Historical Sources 

  The  data  of  historical  sources  is  subject  to  two  types  of  evaluation.  These  two  types  are:  (i) 
external evaluation or criticism and (ii) internal evaluation or criticism. Let us now look at these in detail. 

(i) External Criticism of Data:  

  This  is  sometimes  also  known  as  lower  criticism  of  data.    External  criticism  regards  the  issue  of 
authenticity of the data from the psychological attitude of the researcher in that it is primarily concerned 
with  the  question,  is  the  source  of  data  genuine?  External  criticism  seeks  to  determine  whether  the 
document or the artifact that the researcher is studying is genuinely valid primary data.  It is possible to 
get  counterfeit  documents  or  artifacts.    External  criticism  of  the  sources  of  data  is  of  paramount 
importance in establishing the credibility of the research.  Although, theoretically, the main purpose of 
external criticism is the establishment of historical truth, in reality its actual operation is chiefly restricted 
to the negative role i.e. to identity and expose forgeries, frauds, hoaxes desertions and counterfeits.  In 
order  to  identify  such  forgeries,  researcher  needs  to  look  at  problems  pertaining  to  plagiarism, 
alterations  of  document,  insertions,  deletions  or  unintentional  omissions.    This  will  reveal  whether  the 
historical  source  of  data  is  authentic  or  not.    Establishing  authenticity  of  documents  may  involve 
carbondating, handwriting analysis, identification of ink and paper, vocabulary usage, signatures, script, 
spelling,  names  of  places  and  writing  style  and  other  considerations.    In  other  words,  it  examines  the 
document and its external features rather than the statements it contains.  It tries to determine whether 
(a) the information it contains was available at the time the document was written? (b) this information 
is consistent with what is known about the author or the period from another source? 

In  other  words,  external  criticism  is  aimed  at  answering  questions  about  the  nature  of  the 
historical source such as who wrote it?  Where?  When?  Under which circumstances?  Is it original?  Is it 
genuine?  and so on. 

ii) Internal Criticism of Data :  

Having  established  the  authenticity  of  the  source  of  historical  data,  the  researcher  now  focuses 
his/her attention on the accuracy and wroth of the data contained in the document.  Internal criticism is 
concerned with the meaning of the written material.  It is also known as higher criticism of data.  It deals 
answering questions such as what does it mean?  What was the author attempting to say?  What thought 
was  the  author  trying  to  convey?    Is  it  possible  that  people  would  act  in  the  way  described  in  the 
document?  Is it possible that events described occurred so quickly?  What inferences or interpretations 
could be extracted from these words?  Do the financial data / figures mentioned in the document seem 
reasonable for that period in the past?  What does the decision of a court mean?  What do the words of 
the  decision  convey  regarding  the  intent  and  the  will  of  the  count?    Is  there  any  (unintended) 
misinformation  given  in  the  document?    Is  there  any  evidence  of  deception?    and  so  on      here,  the 
researcher  needs  to  be  very  cautious  so  that  he  does  not  reject  a  statement  only  because  the  event 
described in the document appears to be improbable. 

  In  addition  to  answering  these  questions,  internal  criticism  should  also  include  establishing  the 
credibility  of  the  author  of  the  document.    According  to  Travers,  the  following  questions  could  be 
answered  so  as  to  establish  the  author’s  credibility  :  Was  he  a  trained  or  untrained  observer  of  the 
event?  i.e. How competent was he?  What was his relationship to the event?  To what extent was he 
under pressure, from fear or vanity resulting in distortion or omission of facts?  What was the intent of 
the writer of the document? To what extent was he an expert at recording the particular event?  Were 
the  habits  of  the  author  such  that  they  might  interfere  with  the  accuracy  of  recording?    Was  he  too 
antagonistic  or  too  sympathetic  to  give  a  true  picture?    How  long  after  the  event  did  he  record  his 
testimony?    Was  he  able  to  remember  accurately?    Is  he  in  agreement  with  other  independent 
witnesses? 

These questions need to be answered for two reasons : 

i)  Perceptions are individualized and selective.  Even if eyewitnesses are competent and truthful, they 
could still record different descriptions of the events they witnessed or experienced. 

ii)  Research studies in Psychology indicate that eye witnesses can be very unreliable, especially if they 
are emotionally aroused or under stress at the time of the event.  (e.g. at the time of demolition of 
Babri Masjid or at the time of Gujarat riots in 2002. 

  This  brings  us  to  the  question  of  bias  especially  when  life  histories  or  communal  situations  are 
being studied.  According to Plummer, there are three possible sources of bias as follows : 

Source One : The Life History Informant  

  Is misinformation (unintended) given? 

  Has there been evasion? 

  Is there evidence of direct lying and deception? 

  Is a ‘front’ being presented? 

What may the informant ‘take for granted’ and hence not reveal? 

  How far is the informant ‘pleasing you’? 
  How much has been forgotten? 

  How much may be self‐deception? 

Source Two : The Social Scientist Research  

    Could any of the following be shaping the outcome? 

  (a) Attitudes of researcher : age, gender, class, race etc. 

  (b) Demeanour of researcher : dress, speech, body language etc. 

  (c)  Personality of researcher : anxiety, need for approval, hostility, warmth etc. 

  (d) Attitudes researcher: religion, politics, tolerance, general assumptions 

  (e) Scientific role of researcher: theory held etc. (researcher expectancy) 

Source Three : The Interaction 

   The joint act needs to be examined.  Is bias coming from  

  (a) The physical setting – ‘social’ space 
  (b) The prior interaction? 
  (c)  Non‐verbal communication? 
  (d) Vocal behavior? 
 
  Often,  internal  and  external  criticism  are  interdependent  and  complementary  processes.    The 
internal and external criticism of data require a high level of scholarship. 
 
 
 
D.  Analysis, Synthesis, Summarizing and Interpretation of  Data : 
  We  have  seen  how  data  can  be  located  and  evaluated.    Let  us  now  look  at  how  to  collect  and 
control  the  data  so  that  the  greatest  return  from  the  innumerable  hours  spent  in  archives,  document 
rooms and libraries can be reaped.  The research should not only learn how to take notes but also learn 
how to organize the various notes, note cards, bibliography cards and memoranda so as to derive useful 
and  meaningful  facts  for  interpretation.    Hence  before  beginning  historical  research,  the  researcher 
should have a specific and systematic plan for the acquisition, organization, storage and retrieval of the 
data.  Following are some suggestions that may help you in systematizing your research efforts. 
 

(i)  Note cards and Bibliography Cards : 
  It would be convenient for you to prepare bibliography cards of size 3 × 5 inches for taking down 
bibliographical notes.  A bibliography card is valuable not only for gathering and recording of information 
but  also  for  locating  it  again  at a  future  date,  if  necessary,  without  going  back to  the library  again  and 
again.  Such a card contains the essential information concerning a bibliographical source.  Keep plenty of 
such  cards  with  you  when  you  go  to  the  library  so  that  you  can  report  very  valuable  references 
encountered unexpectedly.  You can also note down the document’s relation to your research.  A sample 
of a bibliographic reference card could be as follows : 
 
Serial No. __________ 
 
 
 
Author(s) : ___________ 
 
Title of the Document : ______________________________________ 
 
Name of the Journal : _______________________________________ 
 
Vol. _____  No. _____ Month ______ Year ______ Page No.(s) _____ 
 
 
 
Place  of  publication,  Name  of  Publisher,  Edition,  Year,  Page  (in  case  of  a 
 
book : ________________________________________________ 
 
 
 
Library where information is obtained : _________________________ 
 

  You can ideally have two copies of such a bibliographic card.  One copy can be arranged according 
to  the  authors’  names  alphabetically  whereas  the  other  copy  can  be  can  be  arranged  as  per  serial 
number of the card. 

  On  the  other  hand,  a  note  card  can  be  of  size  4 × 6  or  5 × 7  inches  for  substantive  notes.    It  is 
advisable  to  place  only  one  item  of  information  on  each  card.    Each  card  can  be  given a  code  so as  to 
indicate the place / question / theme / period / person to which the note relates.  These cards then can 
be  arranged  as  per  the  question,  theme,  period,  place  or  person  under  study  so  as  to  make  analysis 
easier.    In  other  words,  note  cards  can  be  kept  in  multiple  copies.    (e.g.  in  triplicate  or  quadruplicate) 
depending on the ultimate analysis of the data.  Given here is a sample note card. 

 
Main Heading : __________________________    Card No. 
 
________________________________________________________ 
 
Sub – Heading : __________________________________________ 
 
       __________________________________________ 
 
 
 
 
 
Source : Author : _________ Year : _________ pp._________ 
 
 
     Title : __________ Bibliography card No. __________ 
 

   

In  this  card,  one  can  mention  the  bibliography  card  no.  which  can  be  referred  to  for  further 
information it required.  The reverse of the card can be used if the space is found to be insufficient for 
necessary information. 

(ii)  Summary of Quantitative Data : 

  Usually historical studies are chiefly qualitative in nature since the data obtained includes verbal 
and  /  or  symbolic  material  from  an  institution,  society  or  culture’s  past.    However,  when  the  study 
involves quantitative data pertaining to the past events, you need to think carefully about the relevance 
of  the  data  to  your  research.    This  is  because  recording  and  analysis  of  quantitative  data  is  time‐
consuming  and  sometimes  expensive.    Examples  of  quantitative  data  in  historical  research  include 
records  of  students’  and  teachers’  attendance  rates,  examination  results,  financial  information  such  as 
budgets,  income  and  expenditure  statements,  salaries,  fees  and  so  on.    Content  analysis  is  one  of  the 
methods  involving  quantitative  data.    The  basic  goal  of  content  analysis  is  to  take  a  verbal,  non‐
quantitative document and transform it into quantitative data. 

 
 

(iii)  Interpretation of Historical Data : 

  Once the researcher establishes the validity and authenticity of data, interpretation of the facts in 
the light of the topic of research is necessary.  This step requires caution, imagination, ingenuity, insight 
and  scholarliness.    The  scientific  status  of  his  study  depends  on  these  characteristics.    The  researcher 
needs to be aware of his/her biases, values, prejudices and interest as these could influence the analysis 
and interpretation of the data as well as the perceptions of the researcher.  He needs to make sense out 
of the multitude of data gathered which generally involves a synthesis of data in relation to a hypothesis 
or  question  or  theory  rather  than  mere  accumulation  or  summarization.    In  doing  so,  he  /  she  should 
avoid  biases  and  unduly  projecting  his  /  her own  personality  onto  the  data.   The  data  should  be  fitted 
into  a  logically  parsimonious  structure.    The  researcher  should  be  clear  about  the  interpretative 
framework  so  as  to  become  sensitive  towards  bias  in  other  historical  researchers’  interpretations  who 
have conducted research on the same or similar topics.   

  In historical research, ‘causes’ are in the form of antecedents or precipitating factors.  They are not 
‘causes’ in the strictly scientific sense.  Such antecedents are always complex and hence the researcher 
should avoid over simplification while interpreting them.  Past events are mainly in the form of human 
behaviour.    Therefore  ‘causes’  in  historical  research  could  be  interpreted  in  terms  of  motives  of  the 
participants involved. 

  The  researcher  needs  to  identify  the  motives  of  the  people  involved  in  the  event  under  study 
while interpreting the data.  These motives may be multiple in nature and interact with each other.  This 
makes interpretation of the data a difficult task.  For example, a new government decides to change the 
prevalent textbooks.  The motives here could be many such as its political ideology does not match the 
prevalent  textbooks,  it  had  a  personal  grudge  against  the  authors  of  the  prevalent  textbooks  or  the 
ministers  concerned  wanted  to  derive  personal  glory  out  of  his  actions.    These  reasons  may  influence 
each other making the task of interpretation of data difficult. 

  Historical  researchers  can  make  use  of  concepts  from  other  social  and  behavioural  science 
disciplines  in  analyzing  interpreting  data.    Some  examples  of  such  concepts  may  be  bureaucracy,  role, 
institution  (from  sociology),  leadership,  institutional  effectiveness  (From  management),  culture  (from 
anthropology), motive, personality attitude etc. (from psychology) and so on. 
 
  The  researcher  also  can  make  use  of  the  concepts  of  historical  time  and  historical  space  white 
interpreting the data. 
 

  The concept of historical time makes use of a chronology of events. i.e. the researcher needs to 
identify the chain of events (chronology) of substantive history and then try to understand the meaning 
of  these  events,  the  relationship  among  the  events  and  the  relationship  of  the  events  to  the  research 
topic.  The researcher is studying more than one set of chronological data within the same time frame 
may gain increased insight into multiple events and their causes. 
 

  The  concept  of  historical  space  deals  with  ‘where’  the  event  originated,  spread  or  culminated.  
This could provide a different insight into the meaning of the data. 

  The historical researcher can also use analogy as a source of hypothesis or as a frame of reference 
for interpretation.  i.e. He / she can draw parallels between one historical event and other events.  Here, 
one  has  to  be  aware  of  similarities,  differences  as  well  as  exceptions  while  comparing  two  historical 
events,  otherwise,  such  an  extrapolation  will  be  unreliable.    Also,  it  is  risky  to  interpret  an  event  by 
comparing with another event in another culture at another time. 
 

iv) Making Inferences and Generalizations in Historical Research: 

  in order to identify and explain the ‘cause/s’ of a historical event, the research must be aware of 
his/ her assumptions which are then used in ascribing causation to subsequent events.  Some examples 
of  such  assumption  could  include  (i)  history  repeats  itself,  or  (ii)  historical  events  are  unique.    The 
researcher must make clear whether his / her analysis is based on the former assumption or the latter. 
 

Some  examples  of  ‘causes’  of  historical  events  identified  in  prior  researches  include  (i)  strong 
ideology  (eg.  Maharshi  Karve’s  ideology  of  women’s  education)  (ii)  actions  of  certain  key  persons  (e.g. 
Mohamed  Ali  Jinnah’s  actions  for  India’s  partition),    (iii)  Advances  in  Science  in  technology  (e.g.  use  of 
computers  in  education),  (iv)  economic  /  geographical  /  psychological  /  sociological  factors  or  a 
combination of all these (e.g. privatization of education) etc. 
 

  The historian’s objective is not only to establish facts but also to determine trends in the data and 
causes of events leading to generalizations i.e. he / she needs to synthesize and interpret and not merely 
summarize  the  data.    These  data,  as  in  other  types  of  researches,  are  obtained  not  from  the  entire 
population  of  persons,  settings,  events  or  objects  pertaining  to  the  topic,  but  from  a  small  sample.  
Moreover, this sample is selected from the remains of the past.  It can not be selected from the entire 
population of documents or relics that existed during the period under study.  Such remains may not be 
representative.  This necessitates a very careful and cautious approach in locating consistency in different 
documents  and  relics  while  making  generalizations.    Also,  the  researcher  should  not  rely  on  only  one 
document pertaining to an individual from the past while making a generalization as it will not be known 
whether the individual held a particular opinion about an educational issue consistently or had changed it 
over a period of time.  If he had changed his opinion, the researcher must find out when and how it was 
changed,  under  what  conditions  and  what  were  the  consequences.    This  makes  it  imperative  that  the 
researcher uses as many primary and secondary sources as possible on a topic.  If the evidence is limited, 
he needs restrict the generalizability of his interpretations to that extent. 

E) Writing the Research Report : 

  This  task  involves  the  highest  level  of  scholarship.    In  a  historical  research,  data  collection  is 
flexible.    Besides,  due  to  the  relative  lack  of  conclusive  evidence  on  which  valid  generalizations  can  be 
established,  the  writing  of  historical  research  has  to  be  a  little  freer  so  as  to  allow  subjective 
interpretation  of  the  data.    (This  by  no  means  implies  distortion  of  truth).    Thus  reports  of  historical 
research  have  no  standard  formats.  The  presentation  of  data  analysis,  interpretations  and  the  findings 
depend on the nature of the problem. 

  There are several board ways of reporting historical investigation as follows : 

i)  The researcher can report the historical facts as answers to different research questions.  Answer to 
each question could be reported in a separate chapter. 
ii)  He  /  she  can  present  the  facts  in  a  chronological  order  with  each  chapter  pertaining  to  a  specific 
historical period chronologically. 
iii)  Report can also written in a thematic manner where each chapter deals with a specific theme / topic. 
iv)  Chapters could also deal with each state of India or each district of an Indian state separately. 
v)  Chapter could also pertain to specific historical persons separately. 
vi)  The researcher can also combine two or more of these approaches while writing the research report. 
 

  In  addition,  the  report  should  contain  a  chapter  each  on  introduction,  methodology,  review  of 
related literature, findings, the researcher’s interpretations and reflections on the interpretative process. 
 

Check Your Progress – II 
 

Q1. Explain how will you identify a research topic for studying the history of education? 
 

2. What are the different sources of historical data? How will you evaluate these sources? 

3. What care will you take in making inferences and generalizations in historical research? 

4. How will you organize writing the research report?  

 
  The researcher needs to demonstrate his / her scholarship and grasp of the topic, his / her insights 
into the topic, and the plausibility and clarity of interpretations.  This requires creativity, ingenuity and 
imagination so as to make the research report adequate and comprehensive. 

6.8 PROBLEMS AND WEAKNESSES TO BE AVOIDED IN HISTORICAL RESEARCH 

  Some of the weaknesses, problems and mistakes that need to be avoided in a historical research 
are as follows : 

1.  The problem of research should not be too broad.   
2.  It  should  be  selected  after  ensuring  that  sources  of  data  are  existent,  accessible  and  in  a  language 
known to the researcher. 
3.  Excessive use of easy‐to‐find secondary sources of data should be avoided.  Though locating primary 
sources of data time‐consuming and requires efforts, they are usually more trustworthy. 
4.  Adequate internal and external criticism of sources of historical data is very essential for establishing 
the  authenticity  and  validity  of  the  data.    It  is  also  necessary  to  ascertain  whether  statements 
concerning evidence by one participant have influenced opinions of other participant or witnesses. 
5.  The  researcher  needs  to  be  aware  of  his/her  own  personal  values,  interests  and  biases.  For  this 
purpose, it is necessary for the researcher to quote statements alongwith the context in which they 
were made. Lifting them out of context shows the intention of persuading the readers. The researcher 
also  needs  to  avoid  both‐extreme  generosity  or  admiration  as  well  as  extreme  criticism.  The 
researcher needs to avoid reliance on beliefs such as “old is gold” “new is always better” or “change 
implies progress”. All such beliefs indicate researcher’s bias and personal values.  

6.  The  researcher  needs  to  ensure  that  the  concepts  borrowed  from  other  disciplines  are  relevant  to 
his/her topic. 

7.  He/She  should  avoid  unwarranted  causal  inferences  arising  on  account  of  (i)  oversimplification 
(causes  of  historical  event  may  be  multiple,  complex  and  interactive),  (ii)  Faulty  interpretation  of 
meanings of words, (iii) inability to distinguish between facts, opinions and situations, (iv) inability to 
identify and discard irrelevant or unimportant facts and (v) Faulty generalization based on inadequate 
evidence,  faulty  logic  and  reasoning  in  the  analysis  of  data,  use  of  wrong  analogy  and  faulty 
comparison of events in unsimilar cultures. 

8.  The researcher needs to synthesize facts into meaningful chronological and thematic patterns. 

 
9.  The  report  should  be  written  in  a  logical  and  scientific  manner.  It  should  avoid  flowery  or  flippant 
language, emotional words, dull and colourless language or persuasive style. 

10. The  researcher  should  avoid  projecting  current  problems  onto  historical  events  as  this  is  likely  to 
create distortions. 

6.9 CRITERIA OF EVALUATING HISTORICAL RESEARCH : 

  Mouly has provided the following criteria of evaluating historical research: 

1.  Problem: Has the problem been clearly defined? It is difficult enough to conduct historical research 
adequately without adding to the confusion by starting out with a nebulous problem. Is the problem 
capable of solution? Is it within the competence of the investigator? 

2.  Data: Are data of a primary nature available in sufficient completeness to provide a solution, or has 
there been an overdependence on secondary or unverifiable sources? 

3.  Analysis:  Has  the  dependability  of  the  data  been  adequately  established?  Has  the  relevance  of  the 
data been adequately explored?  

4.  Interpretation:  Does  the  author display  adequate  mastery  of  his data  and  insight  into  their  relative 
significance? Does he display adequate historical perspective? Does he maintain his objective or does 
he  allow  personal  bias  to  distort  the  evidence?  Are  his  hypotheses  plausible?  Have  they  been 
adequately  tested?  Does  he  take  a  sufficiently  broad  view  of  the  total  situation?  Does  he  see  the 
relationship between his data and other ‘historical facts’? 

5.  Presentation: Does the style of writing attract as well as inform? Does the report make a contribution 
on the basis of newly discovered data or new interpretation, or is it simply ‘uninspired back work’? 
Does it reflect scholarliness? 

Check your Progress III 

1. What care will you take to avoid weaknesses in conducting historical research? 
 

2. State the criteria of evaluating historical research.  

Suggested Readings: 
 

Garraghan, G. J. A Guide to Historical Method. New York: Fordham University Press. 1946.
Gottschalk, L. Understanding History. New York : Alfred A. Knopf. 1951.
McMillan, J. H. and Schumacher, S. Research in Education : A Conceptual Introduction. Boston, MA :
Little, brown and Company. 1984.
Shafer, R. J.  A Guide to Historical Method. Illinois : The Dorsey Press. 1974.  
 7

EXPERIMENTAL RESEARCH
 

Unit Structure
 

7.0 Objectives 

7.1 Introduction 

72  Experimental Designs 

    a. Pre‐experimental design 

    b. Quasi‐experimental design 

    c. True experimental design 

7.3 Factorial Design 

7.4 Nested Design 

7.5 Single Subject Design 

7.6 Internal and External Experimental Validity 

7.7 Controlling Extraneous and Intervening Variables 

7.0 OBJECTIVES :
 

After going through this module, you will be able to: 

(i) Conceptualize experimental method of Educational research; 
(ii) Describe the salient features of experimental research; on 
(iii) Conceptualize various experimental design 
(iv) Conceptualize the internal and external experimental validity 
(v) Conceptualize the process of controlling the intervening and extraneous variables; and 
(vi) Apply experimental method for appropriate research problem. 

7.1 INTRODUCTION :

The experimental method in educational research is the application and adaptation of the classical
method of experimentation. It is a scientifically sophisticated method. It provides a method of
investigation to derive basic relationships among phenomena under controlled condition or, more simply,
to identify the conditions underlying the occurrence of a given phenomenon. Experimental research is the
description and analysis of what will be, or what will occur, under carefully controlled conditions.

Experimenters  manipulate  certain  stimuli,  treatments,  or  environmental  conditions  and  observe 
how the condition or behaviour of the subject is affected or changed. Such manipulations are deliberate 
and  systematic.  The  researchers  must  be  aware  of  other  factors  that  could  influence the  outcome  and 
remove  or  control  them  in  such  a  way  that  it  will  establish  a  logical  association  between  manipulated 
factors and observed factors.  

  Experimental  research  provides  a  method  of  hypothesis  testing.  Hypothesis  is  the  heart  of 
experimental research. After the experimenter defines a problem he has to propose a tentative answer 
to the problem or hypothesis. Further, he has to test the hypothesis and confirm or disconfirm it.  

  Although,  the  experimental  method  has  greatest  utility  in  the  laboratory,  it  has  been  effectively 
applied non‐laboratory settings such as the classroom. The immediate purpose of experimentation is to 
predict  events  in  the  experimental  setting.  The  ultimate  purpose  is  to  generalize  the  variable 
relationships so that they may be applied outside the laboratory to a wider population of interest.   

Characteristics of Experimental Method  
 

  There are four essential characteristics of experimental research: (i) Cool, (ii) Manipulationtrn, (iii) 
Observation, and (iv) Replication.  

Control : Variables that are not of direct interest to the researcher, called extraneous variables, need to 
be  controlled.  Control  refers  to  removing  or  minimizing  the  influence  of  such  variables  by  several 
methods  such  as:  randomization  or  random  assignment  of  subjects  to  groups;  matching  subjects  on 
extraneous  variable(s)  and  then  assigning  subjects  randomly  to  groups;  making  groups  that  are  as 
homogenous  as  possible  on  extraneous  variable(s);  application  of  statistical  technique  of  analysis  of 
covariance (ANCOVA); balancing means and standard deviations of the groups.  

Manipulation : Manipulation refers to a deliberate operation of the conditions by the researcher. In this 
process,  a pre‐determined  set  of  conditions,  called  independent  variable  or  experimental  variable.  It  is 
also  called  treatment  variable.  Such  variables  are  imposed  on  the  subjects  of  experiment.  In  specific 
terms  manipulation  refers  to  deliberate  operation  of  independent  variable  on  the  subjects  of 
experimental  group  by  the  researcher  to  observe  its  effect.  Sex,  socio‐economic  status,  intelligence, 
method  of  teaching,  training  or  qualification  of  teacher,  and  classroom  environment  are  the  major 
independent variables in educational research. If the researcher, for example, wants to study the effect 
of ‘X’ method of teaching on the achievement of students in mathematics, the independent variable here 
is the method of teaching. The researcher in this experiment needs to manipulate ‘X’ i.e. the method of 
teaching. In other words, the researcher has to teach the experimental groups using ‘X’ method and see 
its effect on achievement.  

Observation : In experimental research, the experimenter observes the effect of the manipulation of the 
independent variable on dependent variable. The dependent variable, for example, may be performance 
or achievement in a task. 

Replication : Replication is a matter of conducting a number of sub‐experiments, instead of one 
experiment only, within the framework of the same experimental design. The researcher may make a 
multiple comparison of a number of cases of the control group and a number of cases of the 
experimental group. In some experimental situations, a number of control and experimental groups, 
each consisting of equivalent subjects, are combined within a single experiment. 

Check your progress – 1

 

Q.1) What are the characteristics of experimental research? 

7.2 EXPERIMENTAL DESIGNS :

 

Experimental design is the blueprint of the procedures that enable the researcher to test hypotheses
by reaching valid conclusions about relationships between independent and dependent variables (Best,
1982, p.68). Thus, it provides the researcher an opportunity for the comparison as required in the
hypotheses of the experiment and enables him to make a meaningful interpretation of the results of the
study. The designs deal with practical problems associated with the experimentation such as: (i) how
subjects are to be selected for experimental and control groups, (ii) the ways through which variables are to
be manipulated and controlled, (iii) the ways in which extraneous variables are to be controlled, how
observations are to be made, and (iv) the type of statistical analysis to be employed.

Variables are the conditions or characteristics that the experimenter manipulates, controls, or
observes. The independent variables are the conditions or characteristics that the experimenter manipulates
or controls in his or her attempt to study their relationships to the observed phenomena. The dependent
variables are the conditions or characteristics that appear or disappear or change as the experimenter
introduces, removes or changes the independent variable. In educational research teaching method is an
example of independent variable and the achievement of the students is an example of dependent variable.
There are some confounding variables that might influence the dependent variable. Confounding variables
are of two types; intervening and extraneous variables. Intervening variables are those variables that
cannot be controlled or measured but may influence the dependent variable. Extraneous variables are not
manipulated by the researcher but influence the dependent variable. It is impossible to eliminate all
extraneous variables, but sound experimental design enables the researcher to more or less neutralize their
influence on dependent variables.

  There are various types of experimental designs. The selection of a particular design depends upon 
factors like nature and purpose of experiment, the type of variables to be manipulated, the nature of the 
data,  the  facilities  available  for  carrying  out  the  experiment  and  the  competence  of  the  experimenter. 
The following categories of experimental research designs are popular in educational research: 

(i)  Pre‐experimental  designs  –  They  are  least  effective  and  provide  little  or  no  control  of  extraneous 
variables. 

(ii)  True  experimental  designs  –  employ  randomization  to  control  the  effects  of  variables  such  as 
history, maturation, testing, statistical regression, and mortality. 

(iii)  Quasi‐experimental  designs  –  provide  less  satisfactory  degree  of  control  and  are  used  only  when 
randomization is not feasible. 

(iv)   Factorial designs‐ more than one independent variables can be manipulated simultaneously. Both 
independent and interaction effects of two or more than two factors can be studied with the help of 
this factorial design. 

Symbols used :
In discussing experimental designs a few symbols are used. 
E – Experimental group 

C – Control group 

X – Independent variable 

Y – Dependent variable 

R – Random assignment of subjects to groups 

Yb – Dependent variable measures taken before experiment / treatment (pre‐test) 

Ya – Dependent variable measures taken after experiment/ treatment (Post‐test) 

Mr – Matching subjects and then random assignment to groups. 
a. Pre-Experimental design :
 

There are two types of pre‐experimental designs: 

1.  The one group pre‐test post‐test design : 

This is a simple experimental research design without involvement of a control group. In this design
the experimenter takes dependent variable measures (Yb) before the independent variable (X) is
manipulated and again takes its measures (Ya) afterwards: The difference if any, between the two
measurements (Yb and Ya) is computed and is ascribed to the manipulation of X.
 

  Pre‐test    Independent variable  Post‐test 

  Yb        X          Ya 

The  experimenter,  in  order  to  evaluate  the  effectiveness  of  computer‐based  instruction  (CBI)  in 
teaching of science to grade V students, administers an achievement test to the whole class (Yb) before 
teaching through CBI. The test is administered over the same class again to measure Ya. The means of Yb 
and Ya are compared and the difference if any is ascribed to effect of X, i.e. teaching through CBI. 

The  design  has  the  inherent  limitation  of  using  one  group  only.  The  design  also  lacks  scope  of 
controlling extraneous variables like history, maturation, pre‐test sensitization, and statistical regression 
etc. 

2.  The two groups static design : 

This design provides some improvement over the previous by adding a control group which is not
exposed to the experimental treatment. The experimenter may take two sections of grade-V of one school
or grade-V of one school or grade-V students of two different schools (intact classes) as experimental and
control groups respectively and assume the two groups to be equivalent. No pre-test is taken to ascertain it.
         Group    Independent Variable    Post‐test 

  E      X             Ya 

  C      ‐             Ya 

   
 This design compares the post-test scores of experimental group (Ya E) that has received
experimental treatment (X) with that of control group (Ya C) that has not received X.

  The major limitation of the design is that there is no provision for establishing the equivalence of 
the experimental (E) and control (C) groups. However, since no pretest is used, this design controls for 
the effects of extraneous variables such history, maturation, and pre‐testing. 

Check your progress – 2 

Q.2) What is pre‐experimental design? 

b. Quasi‐Experimental Design : 

Researchers commonly try to establish equivalence between the experimental and control groups, 
the  extent they  are  successful  in doing  so;  to  this  extent  the  design  is  valid.  Sometimes  it  is  extremely 
difficult or impossible to equate groups by random selection or random assignment, or by matching. In 
such situations, the researcher uses quasi‐experimental design. 

The Non-Equivalent Groups Design is probably the most frequently used design in social
research. It is structured like a pretest-posttest randomized experiment, but it lacks the key feature of the
randomized designs -- random assignment. In the Non-Equivalent Groups Design, we most often use intact
groups that we think are similar as the treatment and control groups. In education, we might pick two
comparable classrooms or schools. In community-based research, we might use two similar communities.
We try to select groups that are as similar as possible so we can fairly compare the treated one with the
comparison one. But we can never be sure the groups are comparable. Or, put another way, it's unlikely
that the two groups would be as similar as they would if we assigned them through a random lottery.
Because it's often likely that the groups are not equivalent, this designed was named the nonequivalent
group design to remind us.

Pre‐test    Independent Variable      Post‐test 

    Yb  X    Ya (Experimental) 

   Yb  ‐    Ya (Control) 

So, what does the term "nonequivalent" mean? In one sense, it just means that assignment to group
was not random. In other words, the researcher did not control the assignment to groups through the
mechanism of random assignment. As a result, the groups may be different prior to the study. This design
is especially susceptible to the internal validity threat of selection. Any prior differences between the
groups may affect the outcome of the study. Under the worst circumstances, this can lead us to conclude
that our program didn't make a difference when in fact it did, or that it did make a difference when in fact
it didn't.

The  counterbalanced  design  may  be  used  when  the  random  assignment  of  subject  to 
experimental group and control group is not possible. This design is also known as rotation group design. 
In counterbalanced design each group of subject is assigned to experimental treatment at different times 
during  the  experiment.  This  design  overcomes  the  weakness  of  non‐equivalent  design.  When  intact 
groups are used, rotation of groups provides an opportunity to eliminate any differences that might exist 
between the groups. Since all the groups are exposed to all the treatments, the results obtained cannot 
be attributed to the preexisting differences in the subjects. The limitation of this design is that there is 
carry‐over  effect  of  the  groups  from  one  treatment  to  the  next.  Therefore,  this  design  should  be  used 
only  when  the  experimental  treatments  are  such  that  the  administration  of  one  treatment  on  a  group 
will have no effect on the next treatment. There is possibility of boring students with repeated testing. 

Check your progress – 3 

How does pre‐experimental design differ from quasi experimental design? 

c. True experimental design : 
 

True experimental designs are used in educational research because they ascertain equivalence of
experimental and control groups by random assignment of subjects to these groups, and thus, control the
effects of extraneous variables like history, maturation, testing, measuring instruments, statistical
regression and mortality. This design, in contrast to pre-experimental design, is a better and used in
educational research wherever possible.

1.        Two groups, randomized subjects, post‐test only design: 

This is one of the most effective designs in minimizing the threats to experimental validity. In this 
design subjects are assigned to experimental and control groups by random assignment which controls 
all  possible  extraneous  variables,  e.g.  testing,  statistical  regression,  mortality  etc.  At  the  end  of 
experiment the difference between the mean post‐test scores of the experimental and control group are 
put to statistical test –‘t’ test or analysis of variance (ANOVA). If the differences between the means are 
found significant, it can be attributed to the effect of (X), the independent variable.  

Group     Independent Variable        Post‐test 

E        X        Ya 

R
 

  C        ‐           Ya 

The main advantage of this design is random assignment of subjects to groups, which assures the
equivalence of the groups prior to experiment. Further, this design, in the absence of pretest, controls the
effects of history, maturation and pre-testing etc.

  This  design  is  useful  in  the  experimental  studies  at  the  pre‐primary  or  primary  stage  and  the 
situations in which a pre‐test is not appropriate or not available. 

2.  Two groups, randomized matched subject, post‐test only design : 

This design, instead of using random assignment of subjects to experimental and control group, uses
the technique of matching. In this technique, the subjects are paired so that their scores on matching
variable(s), i.e. the extraneous variable(s) the experimenter wants to control, are as close as possible. One
subject of each pair is randomly assigned to one group and the other to the second group. The groups are
designated as experimental and control by random assignment (tossing a coin).

Group     Independent Variable      Post‐test 

E        X        Ya 
MR
C        ‐        Ya 

 
 This design is mainly used where “two groups randomized subjects, post-test only” design is not
applicable and where small groups are to be used. The random assignment of subjects to groups after
matching adds to the strength of this design. The major limitation of the design is that it is very difficult to
use matching as a method of controlling extraneous variables because in some situations it is not possible
to locate a match and some subjects are excluded from the experiment.

3.Two groups randomized subjects, pre‐test post‐test design : 

In this design subjects are assigned to the experimental group and the control group at random and
are given a pre-test (Yb). The treatment is introduced only to the experimental group, after which the two
groups are measured on dependent variable. The difference in scores or gain scores (D) in respect of pre-
test and post-test (Ya – Yb = D) is found for each group and the difference in scores of both the groups (De
and Dc) is compared in order to ascertain whether the experimental treatment produced a significant
change. Unless the effect of the experimental manipulation is strong, the analysis of the differential score
is not advisable (Kerlinger, 1973, p-336). If they are analyzed, however, a ‘t’ or ‘F’ test is used.

Group   Pre‐test  Independent Variable    Post‐test 

   E       Yb      X      Ya 

   C       Yb      ‐      Ya 

The main advantages of this design include: 

• Through initial randomization and pre‐testing equivalence between the two groups can be ensured. 
• Randomization seems to control most of the extraneous variables. 
 

But the design does not guarantee external validity of the experiment as the pretest may increase 
the subjects’ sensitivity to the manipulation of X.  

4.  The Solomon three groups design : 

This design, developed by Solomon seeks to overcome the difficulty of the design: Randomized
Groups, Pre-test Posttest Design, i.e. the interactive effects of pre-testing and the experimental
manipulation. This is achieved by employing a second control group (C2) which is not pre-tested but is
exposed to the experimental treatment (X).
 

Group        Pre‐test    Independent Variable   Post‐test 

E    Yb      X      Ya 

C1    Yb      ‐      Ya 

 C2    ‐      X      Ya 

This design provides scope for comparing post‐tests (Ya) scores for the three groups. Even though 
the  experimental  group  has  a  significantly  higher  mean  score  as  compared  to  that  of  the  first  control 
group (YaE  > Ya C1), one cannot be confident that this difference is due to the experimental treatment (X). 
It might have occurred because of the subjects’ pre‐test sensitization. But, if the mean Ya scores of the 
second control group is also higher as compared to that of the first control group (Ya C2 > Ya Cl), then one 
can  assume  that  the  experimental  treatment  has  produced  the  difference  rather  than  the  pre‐test 
sensitization, since C2 is not pre‐tested. 

5.  The Solomon four group design : 

This design is an extension of Solomon three group design and is really a combination of two two-
groups designs: (i) Two groups randomized subjects pre-test post-test design; and (ii) Two group
randomized subjects post-test only design. This design provides rigorous control over extraneous variables
and also provides opportunity for multiple comparisons to determine the effects of the experimental
treatment (X).

In  this  design  the  subjects  are  randomly  assigned  to  the  four  groups.  One  experimental  (E)  and 
three  control  (Cl,  C2  and  C3).  The  experimental  and  the  first  control  group  (E  and  C1)  are  pre‐tested 
groups, and the second and third control groups (C2 and C3) are not pre‐tested groups. If the post‐test 
mean scores of experimental group (Ya E) is significantly greater than the post‐test mean score of the first 
control group (Ya C1); and also the post test mean score of the second control group (Ya C2) is significantly 
greater than the post‐test mean score of the third control group (Ya C3), the experimenter arrives at the 
conclusion that the experimental treatment (X) has effect. 

  Group  Pre‐test  Independent Variable Post test 

  E  Yb  X Ya

  C1  Yb  ‐ Ya

R     

  C2  ‐  X Ya

  C3  ‐  ‐ Ya

This design is considered to be strong one as it actually involves conducting the experiment twice,
once with pre-test and once without pre-test. Therefore, if the results of these two experiments are in
agreement, the experimenter can have much greater confidence in his findings. The design seems to have
two sources of weakness. One is practicability as it is difficult to conduct two simultaneous experiments,
and the researcher encounters the difficulty of locating more subjects of the same kind. The other difficulty
is statistical. Since the design involves four sets of measures for four groups and the experimenter has to
make comparison between the experimental and first control group and between second and third control
groups there is no single statistical procedure that would make use of the six available measures
simultaneously.

Check your progress – 4

How does true experimental design differ from quasi experimental design?

7.3 FACTORIAL DESIGN : 

Experiments may be designed to study simultaneously the effects of two or more variables. Such 
an experiment is called factorial experiment. Experiments in which the treatments are combinations of 
levels of two or more factors are said to be factorial. If all possible treatment combinations are studied, 
the experiment is said to be a complete factorial experiment. When two independent factors have two 
levels  each,  we  call  it  as  2x2  (spoken  "two‐by‐two”)  factorial  design.  When  three  independent  factors 
have  two  levels  each,  we  call  it  2x2x2  factorial  design.  Similarly,  we  may  have  2x3,  3x3,  3x4,  3x3x3, 
2x2x2x2, etc. 

Simple Factorial Design : 

A simple factorial design is 2x2 factorial design. In this design there are two independent variables 
and  each  of  the  variables  has  two  levels.  One  advantage  is  that  information  is  obtained  about  the 
interaction of factors. Both independent and interaction effects of two or more than two factors can be 
studied with the help of this factorial design. 

In factorial designs, a factor is a major independent variable. In this example we have two factors: 
methods  of  teaching  and  intelligence  level  of  the  students.  A  level  is  a  subdivision  of  a  factor.  In  this 
example,  method  of  teaching  has  two  levels  and  intelligence  has  two  levels.  Sometimes  we  depict  a 
factorial  design  with  a  numbering  notation.  In  this  example,  we  can  say  that  we  have  a  2  x  2  (spoken 
"two‐by‐two”) factorial design. In this notation, the number of numbers tells us how many factors there 
are and the number values tell how many levels. The number of different treatment groups that we have 
in  any  factorial  design  can  easily  be  determined  by  multiplying  through  the  number  notation.  For 
instance, in our example we have 2x2 = 4 groups. In our notational example, we would need 3 x 4 = 12 
groups.  Full  factorial  experiment  is  an  experiment  whose  design  consists  of  two  or  more  factors,  each 
with discrete possible values or "levels", and whose experimental units take on all possible combinations 
of  these  levels  across  all  such  factors.  A  full  factorial  design  may  also  be  called  a  fully‐crossed  design. 
Such  an  experiment  allows  studying  the  effect  of  each  factor  on  the  response  variable,  as  well  as  the 
effects of interactions between factors on the response variable. 

For the vast majority of factorial experiments, each factor has only two levels. For example, with
two factors each taking two levels, a factorial experiment would have four treatment combinations in total,
and is usually called a 2×2 factorial design. The first independent variable, which is manipulated, has two
values called the experimental variable. The second independent variable, which is divided into levels,
may be called control variable. For example, there are two experimental treatments, that is, teaching
through co-operative learning and teaching through lecture method. It is observed that there may be
differential effects of these methods on different levels of intelligence of the students. On the basis of the
IQ score the experimenter divides the students into two groups: one high intelligent group and the other the
low intelligent group. There are four groups of students within each of the two levels of intelligence.

High Intelligence Low Intelligence

Group Group

Teaching Through Gain Score on the Gain Score on the

Co-operative Dependent Variable Dependent Variable
Learning Method

Teaching Through Gain Score on the  Gain Score on the 

Dependent Variable  Dependent Variable 
Lecture Method

Since one of the objectives is to compare various combinations of these groups, the experimenter
has to obtain the mean scores for each row and each column. The experimenter can first study the main
effect of the two independent variables and the interaction effect between the intelligence level and
teaching method.

Check your progress – 5

1. How does factorial design differ from true experimental design?

 
 

7.4 NESTED DESIGN :

 

  In a nested design, each subject receives one, and only one, treatment condition. In a nested design, 
the levels of one factor appear only within one level of another factor. The levels of the first factor are 
said  to  be  nested  within  the  level(s)  of  the  second  factor.    When  variables  such  as  race,  income  and 
education, etc. may be found only at a particular level of the independent variable, these variables are 
called  nested  variables.  In  these  studies  the  various  nested  variables  are  grouped  for  the  study.  For 
example,  a  researcher  is  studying  school  effectiveness  with  academic  achievement  of  students  as  the 
indicator or criterion variable. In this type of research, school type can be nested within individual schools 
which can be nested within classrooms. The major distinguishing feature of nested designs is that each 
subject  has  a  single  score.  The  effect,  if  any,  occurs  between  groups  of  subjects  and  thus  the  name 
“Between  Subjects”  is  given  to  these  designs.  The  relative  advantages  and  disadvantages  of  nested 
designs are opposite those of crossed designs. First, carry over effects are not a problem, as individuals 
are measured only once. Second, the number of subjects needed to discover effects is greater than with 
crossed  designs.  Some  treatments  by  their  nature  are  nested.  The  effect  of  gender,  for  example,  is 
necessarily  nested.  One  is  either  a  male  or  a  female,  but  not  both.  Religion  is  another  example. 
Treatment  conditions  which  rely  on  a  pre‐existing  condition  are  sometimes  called  demographic  or 
blocking factors. 

Crossed Design :

In a crossed design each subject sees each level of the treatment conditions. In a very simple
experiment, such as one that studies the effects of caffeine on alertness, each subject would be exposed to
both a caffeine condition and a no caffeine condition. For example, using the members of a statistics class
as subjects, the experiment might be conducted as follows. On the first day of the experiment, the class is
divided in half with one half of the class getting coffee with caffeine and the other half getting coffee
without caffeine. A measure of alertness is taken for each individual, such as the number of yawns during
the class period. On the second day the conditions are reversed; that is, the individuals who received coffee
with caffeine are now given coffee without and vice-versa. The size of the effect will be the difference of
alertness on the days with and without caffeine.

The distinguishing feature of crossed designs is that each individual will have more than one score.
The effect occurs within each subject, thus these designs are sometimes referred to as ‘within subjects’
designs.
 Crossed designs have two advantages. One, they generally require fewer subjects, because each
subject is used a number of times in the experiment. Two, they are more likely to result in a significant
effect, given the effects are real.

Crossed designs also have disadvantages. One, the experimenter must be concerned about carry-
over effects. For example, individuals not used to caffeine may still feel the effects of caffeine on the
second day, even though they did not receive the drug. Two, the first measurements taken may influence
the second. For example, if the measurement of interest was score on a statistics test, taking the test once
may influence performance the second time the test is taken. Three, the assumptions necessary when more
than two treatment levels are employed in a crossed design may be restrictive.

Check your progress - 6

1. What is the difference between nested design and crossed design?

7.5  SINGLE FACTOR EXPERIMENT : 
 

Many experiments involve single treatment or variable with two or more levels. First, a group of 
experimental  subjects  may  be  divided  into  independent  groups,  using  a  random  method.  Different 
treatment  may  be  applied  to  each  group.  One  group  may  be  a  control  group,  a  group  to  which  no 
treatment is applied. For meaningful interpretation of experiment, results obtained under treatment may 
be  compared  with  results  obtained  in  the  absence  of  treatment.  Comparison  may  be  made  between 
treatments and between treatment and a control. 

Some  single  factor  experiments  involve  a  single  group  of  subjects.  Each  subject  receives 
treatments. Repeated observations or measurements are made on the same subjects. 

Some single factor experiments may consists of groups that are matched on one or more variables 
which are known to be correlated with the dependent variable. For example IQ may be correlated with 
achievement. 
 

An example of single factor Experiment : 
 
 It is believed that the amount of time a player warms up at the beginning will have a significant 
impact on his game, lawn tennis. The hypothesis is that if he does not warm up at all or only for a brief 
time (less than 15 minutes), he will be stiff and his score will be poor. However, if he warms up too much 
(over  40  minutes),  he  will  be  tired  and  his  game  score  will  also  suffer.  He  needs  to  choose  levels  of 
warming  up  to  test  this  hypothesis  that  are  significantly  different  enough.  The  levels  he  will  test  are 
warming up for 0, 15, 30, and 45 minutes.   

   

7.6 INTERNAL AND EXTERNAL EXPERIMENTAL VALIDITY : 
 

Validity of experimentation :
 

An experiment must have two types of validity: internal validity and external validity (Campbell
and Stanley, 1963):

Internal validity : 
 

Internal validity refers to the extent to which the manipulated or independent variables actually have
a genuine effect on the observed results or dependent variable and the observed results were not affected
by the extraneous variables. This validity is affected by the lack of control of extraneous variables.
External validity :
 

  External validity is the extent to which the relationships among the variables can be generalized 
outside the experimental setting like other population, other variables. This validity is concerned with the 
generalizability or representativeness of the findings of experiment, i.e. to what population, setting and 
variables can the results of the experiment be generalized. 

Factors affecting validity of experimentation : 
 

In educational experiments, a number of extraneous variables influence the results of the

experiment in way that are difficult to evaluate. Although these extraneous variables cannot be completely
eliminated, many of them can be identified. Campbell and Stanley (1963) have pointed out the following
major variables which affect significantly the validity of an experiment:
 

History : The variables, other than the independent variables, that may occur between the first and the 
second measurement of the subjects (Pre‐test and post test). 

Maturation : The changes that occur in the subjects over a period of time and confused with the effects 
of the independent variables. 
 

Testing : Pre‐testing, at the beginning of an experiment, may be sensitive to subjects, which may produce 
a change among them and may affect their post‐test performance. 

Measuring Instruments : Different measuring instruments, scorers, interviewers or the observers used at 
the pre and post testing stages; and unreliable measuring instruments or techniques are threats to the 
validity of an experiment. 

Statistical  regression  :  It  refers  to  the  tendency  for  extreme  scores  to  regress  or  move  towards  the 
common mean on subsequent measures. The subjects who scored high on a pre‐test are likely to score 
relatively low on the retest whereas the subjects who scored low on the pre‐test are likely to score high 
on the retest. 

Experimental mortality : It refers to the differential loss of subjects from the comparison groups. Such 
loss of subjects may affect the findings of the study.  For example, if some subjects in the experimental 
group who received the low scores on the pre‐test drop out after taking the test, this group may show 
higher mean on the post‐test than the control group. 

Differential  selection  of  subjects  :  It  refers  to  difference  between/among  groups  on  some  important 
variables related to the dependent variable before application of the experimental treatment. 

Check your progress – 7

1. What is experimental validity?

7.7 CONTROLLING EXTRANEOUS AND INTERVENING VARIABLES : 
 All experimental designs have one central characteristic: they are based on manipulating the
independent variable and measuring the effect on the dependent variable. Experimental designs result in
inferences drawn from the data that explain the relationships between the variables.

The classic experimental design consists of the experimental group and the control group. In the
experimental group the independent variable is manipulated. In the control the dependent variable is
measured when no alteration has been made on the independent variable. The dependent variable is
measured in the experimental group the same way, and at the same time, as in the control group.

The prediction is that the dependent variable in the experimental group will change in a specific
way and that the dependent variable in the control group will not change.

Controlling Unwanted Influences : 

To obtain a reliable answer to the research question, the design should eliminate unwanted
influences. The amount of control that the researcher has over the variables being studied varies, from
very little in exploratory studies to a great deal in experimental design, but the limitations on control must
be addressed in any research proposal.

These unwanted influences stem from one or more of the following: extraneous variables, bias, the
Hawthorne effect, and the passage of time.

Extraneous Variables : 
 

Extraneous variables are variables that can interfere with the action of the independent variable.
Since they are not part of the study, their influence must be controlled.

In the research literature, the extraneous variables also referred to as intervening variables, directly
affect the action of the independent variable on the dependent variables. Intervening variables are those
variables that occur in the study setting. They include economic, physical, and psychological variables.
Therefore, it is important to control extraneous variables to study the effect of independent variable on
dependent variable. We must be very careful to control all possible extraneous variables that might
intervene the dependant variable.

Methods of controlling extraneous variables include :

• randomization 
• homogeneous sampling techniques 
• matching 
• building the variables into the design 
• statistical control 
 

Randomization : Theoretically, randomization is the only method of controlling all possible 
extraneous variables.  The random assignment of subjects to the various treatment and control groups 
means that the groups can be considered statistically equal in all ways at the beginning of the 
experiment.  It does not mean that they actually are equal for all variables.   

However, the probability of their being equal is greater than the probability of their not being equal,
if the random assignment was carried out properly. The exception lies with small groups where random
assignment could result in unequal distribution of crucial variables. If this possibility exists, the other
method would be more appropriate. In most instances, however, randomization is the best method of
controlling extraneous variables.

A random sampling technique results in a normal distribution of extraneous variables in the sample;
this approximates the distribution of those variables in the population. The purpose of randomization is to
ensure a representative sample.

Randomization comes into play when we randomly assign subjects to experimental and control
groups, thus ensuring that the groups are as equivalent as possible prior to the manipulation of the
independent variable. Random assignment assures that the researcher is unbiased. Instead, assignment is
predetermined for each subject.

Homogeneous Sample : One simple and effective way of controlling an extraneous variable is not to 
allow it to vary. We may choose a sample that is homogenous for that variable. For example, if a 
researcher believes that gender of the subject might affect the dependant variable, he/she could select 
the subjects of the desired gender only. If the researcher believes that socio­economic status might 
influence the dependant variable, he/she would select subject from a particular range of socio­
economic status. After selecting students from a homogenous population the researcher may assign the 
subjects to experimental and control group randomly.   

Matching : When randomization is not possible, or when the experimental groups are too small and 
contain some crucial variables, subjects can be matched for those variables.  The experimenter chooses 
subjects who match each other for the specified variables.  One of these matched subjects is assigned to 
the control group and the other to the experimental group, thus ensuring the equality of the groups at 
the outset.  

The process of matching is time consuming and introduces considerable subjectivity into sample
selection. Therefore, it should be avoided whenever possible. If we use matching, limit the number of
groups to be matched and keep the number of variables for which the subjects are matched low. Matching
with more than five variables becomes extremely cumbersome, and it is almost impossible to find enough
matched partners for the sample. Matching may be used in all research designs when we are looking at
certain outcomes and want to have as much control as possible.

Building Extraneous Variables into the Design : When extraneous variables cannot be adequately 
controlled by randomization, they can be built into the design as independent variables.  They would 
have to be added to the purpose of study and tested for significance along with other variables.  In this 
way, their effect can be measured and separated from the effect of the independent variable.   

Statistical Control : In experimental designs, the effect of the extraneous variables can be subtracted
statistically from the total action of the variables. The technique of analysis of covariance (ANCOVA)
may be used for this purpose. Here, one or more extraneous variables are measured along with the
dependant variables. This method adds to the cost of the study because of the additional data collection
and analysis required. Therefore, it should be used only as a last resort.

Check your progress - 8

1. As an experimenter, how will you control the effect of extraneous and intervening variables?

Unit End Exercise:

• Differentiate between the true experimental design and factorial design. 
• Differentiate between internal and external validity.  
• What is the significance of randomization in experimental research? 

References :

Anderson, G (1990): Fundamentals of Educational Research: The Falmer Press, London.

Best, J.W. & Kahn, J.V. (1993): Research in Education; 7th Ed. Prentice Hall of India Pvt., Ltd., New Delhi. 

Campbell, D. T. & Stanley, J. C. (1963). Experimental and Quasi-Experimental Designs for Research..
Chicago: Rand McNally.
Fisher, R. A. (1959). Statistical Methods & Scientific Inference. New York: Hafner Publishing.
Gay, L.R. (1987). Educational Research, Englewood Cliffs NJ: Macmillan Publishing Company.
Kerlinger, F.N. (1964) : Foundations of Behavioural Research (2nd Ed.), Surjeet Publications, New Delhi. 

Koul,  L.  (1984):  Methodology  of  Educational  Research  (2nd  Ed.),  Vikash  Publishing  House  Pvt.  Ltd.,  New 
Delhi. 

Stockburger,  David  W.  (1998):  Introductory  Statistics:  Concepts,  Models,  and  Applications,  (2nd  Ed), 
www.atomicdogpublishing.com 
 8
 

TOOLS AND TECHNIQUES OF RESEARCH 
 

Unit Structure 

8.0  Steps of Preparing a Research Tool 

8.1  Types of Validity 

8.2  Factors affecting validity 

8.3  Reliability 

8.4  The methods of Estimating Reliability 

8.5  Item Analysis 

8.6  Steps involved in Item – Analysis 

8.0  STEPS OF PREPARING A RESEARCH TOOL: 

  The  first  step  in  preparing  a  research  tool  is  to  develop  a  pool  of  item.  This  is  followed  by  item 
analysis which involves computing difficulty index and discrimination index of each item. This is followed 
by ascertaining the validity of the tool. 

(i)    Validity  :  Validity  is  the  most  important  consideration  in  the  selection  and  use  of  any  testing 
procedures.    The  validity  of  a  test,  or  of  any  measuring  instrument,  depends  upon  the  degree  of 
exactness  with  which  something  is  reproduced/copied  or  with  which  it  measures  what  it  purports  to 
measure. 

   

  The validity of a test may be defined as “the accuracy with which a test measures what it attempts 
to  measure.”  It  is  also  defined  as  “The  efficiency  with  which  a  test  measures  what  it  attempts  to 
measure”. Lindquist has defined validity – “As the accuracy with which it measures that which is intended 
to as the degree to which it approaches infallibility in measuring what it purports to measure”. 
 

  On the basis of the preceding definitions, it is seen that 

• Validity is a matter of degree.  It maybe high, moderate or low. 
• Validity  is  specific  rather  than  general.    A  test  may  be  valid  for  one  specific  purpose  but  not  for 
another Valid for one specific group of students but not for another. 
8.1 TYPES OF VALIDITY : 

(i)  Content Validity : According to Anastasi (1968), “content validity involves essentially the systematic 
examination  of  the  text  content  to  determine  whether  it  covers  a  representative  sample  of  the 
bahaviour domain to be measured”. It refers to how well our tool sample represents the universe of 
criterion  behaviour.  Content  validity  is  employed  in  the  selection  of  items  in  research  tools.  The 
validation of content through competent judgments is satisfactory when the sampling of items is wide 
and judicious.  

(ii) Criterion‐related Validity : This is also known as empirical validity. 

There are two forms of criterion‐related validity. 

a)  Predictive  Validity  :    It  refers  to  how  well  the  scores  obtained  on  the  tool  predict  future  criterion 
behavior. 

b)  Concurrent Validity : It refers to how well the scores obtained on the tool are correlated with present 
criterion behaviour. 

(iii) Construct  Validity  :  It  is  the  extent  to  which  the  tool  measures  a  theoretical  construct  or  trait  or 
psychological variable. It refers to how well our tool seems to measure a hypothesized trait. 
 
 

8.2 FACTORS AFFECTING VALIDITY : 

The following points influence the validity of a test : 

(I)    Unclear Direction :  If directions do not clearly indicate to the respondent how to respond to tool 
items, the validity of a tool is reduced. 

 
(II)      Vocabulary  :    If  the  vocabulary  of  the  respondent  is  poor,  the  he/she  fails  to  respond  to  the  tool 
item, even if he/she knows the answer. It becomes a reading comprehension text for him/her, and 
the validity decreases. 

(III)  Difficult  Sentence  Construction  :    If  a  sentence  is  so  constructed  as  to  be  difficult  to  understand, 
respondents would be confused, which will affect the validity of the tool. 

(IV)  Poorly Constructed Test Items: These reduce the validity of a test. 

(V)  Use of Inappropriate Items :  The use of inappropriate items lowers validity. 

(VI)  Difficulty  Level  of  Items  :    In  an  achievement  test,  too  easy  or  too  difficult  test  items  would  not 
discriminate among students.  Thereby the validity of a test is lowered. 

(VII)  Influence  of  Extraneous  Factors:    Extraneous  factors  like  the  style  of  expression,  legibility, 
mechanics of grammar, (Spelling, punctuation) handwriting, length of the tool, influence the validity 
of a tool. 

(VIII) Inappropriate Time Limit :  In a speed test, if no time limit is given he result will be invalidated.  In a 
power test, an inappropriate time limit will lower its validity.  Our tests are both power and speed 
tests.  Hence care should be taken in fixing the time limit. 

(IX)  Inappropriate  Coverage  :    If  the  does  not  cover  all  aspects  of  the  construct  being  measured 
adequately, its content validity will be adversely affected due to inadequate sampling of items. 

(X)  Inadequate Weightage :  Inadequate weightage to some dimensions, sub‐topics or objectives would 
call into question the validity of tool. 

(XI)  Halo Effect :  If a respondent has formed a poor impression about one aspect of the concept, item, 
person, issue being measured, he/she is likely to rate that concept, item, person, issue poor on all 
other aspects too. Similarly, good impression about one aspect of the concept, item, person, issue 
being measured, he/she is likely to rate that concept, item, person, issue high on all other aspects 
too. This is known as the halo‐effect which lowers the validity of the tool about one aspect of the 
concept,  item,  person,  issue  being  measured,  he/she  is  likely  to  rate  that  concept,  item,  person, 
issue poor on all other aspects too.. 
 

8.3 RELIABILITY :   

  A  test  score  is  called  reliable  when  we  have  reasons  of  believing  the  score  to  be  stable  and 
trustworthy.  If we measure a student s level of achievement, we hope that his score would be similar 
under  different  administrators,  using  different  scores,  with  similar  but  not  identical  items,  or  during  a 
different time of the day.  The reliability of a test may be defined as‐ 

    “The degree of consistency with which the test measures what it does measure”. 

    Anastasi  (1968)  “Reliability  means  consistency  of  scores  obtained  by  same  individual  when  re‐
examined  with  the  test  on  different  sets  of  equivalent  items  or  under  other  variable  examining 
conditions”. 

    A  psychological  or  educational  measurement  is  indirect  and  is  connected  with  less  precise 
instruments or traits that are not always stable.  There are many reasons why a pupil’s test score may 
vary –  

a)  Trait Instability :  The characteristics we measure may change over a period of time. 

b)  Administrative  Error  :    Any  change  in  direction,  timing  or  amount  of  rapport  with  the  test 
administrative may cause score variability. 

c)  Scoring Error :  Inaccuracies in scoring a test paper will affect the scores. 

d)  Sampling Error :  Any particular questions we ask in order to infer a person’s knowledge may affect 
his score. 

e)  Other  Factors  :    Such  as  health,  motivation,  degree  of  fatigue  of  the  pupil,  good  or  bad  luck  in 
guessing may cause score variability. 

8.4 THE METHODS OF ESTIMATING RELIABILITY :   
   

  The four procedures in common use for computing the reliability coefficient of a test 
 

a)  Test – Retest Method  

b)  The Alternate or Parallel Forms Method. 

c)  The Internal Consistency Reliability  

d)  The Inter‐rater Reliability  

a)  Test‐Retest (Repetition) Method (Co‐efficient of Stability) : In test – retest method the single form of 
a test is administered twice on the same sample with a reasonable gap.  Thus two set of scores are 
obtained by administering a test twice.  The correlation Co‐efficient is computed between the two set 
of  scores  as  the  reliability  index.  If  the  test  is  repeated  immediately,  many  subjects  will  recall  their 
first answers and spend their time on new material, thus tending to increase their scores.  Immediate 
memory effects, practice and the confidence induced by familiarity with the material will affect scores 
when  the  test  is  taken  for  a  second  time.    And,  if  the  interval  between  tests  is  rather  long,  growth 
changes will affect the retest score and tends to lower the reliability coefficient. 

A high test – retest reliability or co‐efficient of stability shows that there is low variable error in the 
sets of obtained scores and vice‐versa.  The error variance contributes inversely to the coefficient of 
stability. 

b)  Alternate  or  Parallel  forms  Method  (Co‐efficient  of  Equivalence  Reliability)  :  When  alternative  or 
parallel  forms  of  a  test  can  be  developed,  the  correlation  between  Form‐‘A’  and  Form  ’B’  may  be 
taken as a reliability index. 

The reliability index depends upon the alikeness of two forms of the test.  When the two forms are 
virtually alike, reliability is too high, when they are not sufficient alike, reliability will be too  low. The 
two  forms  of  the  test  are  administered  on  same  sample  of  subjects  on  the  same  day  after  a 
considerable gap. Pearson’s method of correlation is used for calculating of correlation between the 
sets of scores obtained by administering the two forms of the test.  The co‐efficient of correlation is 
termed as co‐efficient of equivalence. 

c)  The Spilt Half Method   (The Co‐efficient of Stability and Equivalence) : The test is administered once 

on  sample  of  subjects.    Each  individual  scope  is  obtained  in  two  parts  (odd  numbers  and  even 
numbers).    The  scoring  is  done  separately  of  these  two  parts  even  numbers  and  odd  numbers  of 
items.    The  co‐efficient  of  correlation  is  calculated  of  two  halves  of  scores.    The  co‐efficient  of 
correlation indicates the reliability of half test.  The self‐correlation co‐efficient of whole test is then 
estimated by using spearman‐Brown Prophecy formula. 
 

d)  The method of ‘Rational Equivalence (Co‐efficient of Internal Consistency) : The method of rational 
equivalence stresses the inter correlations of items in the test and the correlations of the items with 
the test as a whole. The assumption is that all items have the same or equal difficulty value, but not 
necessary the same persons solve each item correctly. 

Factors Influencing Reliability : 

(i)  Interval  :    With  any  method  involving  two  setting  testing  occasions,  the  longer  the  interval  of  time 
between two test administration, the lower the co‐efficient will tend to be. 

(ii) Test Length :  Adding equivalent items makes a test more reliable, while deleting them makes it less 
reliable. 

    A longer test will provide amore adequate sample of the behaviour being measured and the scores 
are apt to be less influenced by chance factors. 

    Lengthening of a test by a number of practical considerations like time, fatigue, boredom, limited 
stock of good items. 

(iii) Inappropriate Time Limit :  A test is considered to be a pure speed test if everyone who reaches an 
item  gets  it  right,  but  no  one  has  the  time  to  finish  all  the  items.    A  power  test  is  one  in  which 
everyone  has  time  to  try  all  the  items  but,  because  of  the  difficulty  level,  no  one  obtains  a  perfect 
score. 

(iv)Group Homogeneity :  Other things being equal, the more heterogeneous the group, the higher the 
reliability.  The test is more reliable when applied to a group of pupils with a wide range of ability than 
one with a narrow range of ability. 

(v) Difficulty of the Items :  Tests in which there is little variability among the scores give lower reliability 
estimates that tests in which the variability is high.  Too difficult or too easy tests for a group will tend 
to be less reliable because the differences among the pupils in such tests are narrow. 

 
(vi)   Objectivity  of  Scoring  :    The  more  subjectively  a  measure  is  scored,  the  lower  its  reliability.  
Objective‐type tests are more reliable than subjective/Essay type tests. 

(vii)  Ambiguous Wording of Items :  When the questions are interpreted in different ways at different 
times by the same pupils, the test becomes less reliable. 

(viii) Inconsistency  in  Test  Administration  :    Such  as  deviations  in  timing,  procedure,  instructions,  etc. 
fluctuations  in  interests  and  attention  of  the  pupils,  Shifts  in  emotional  attitude  make  a  test  less 
reliable. 

(ix)   Optional  Questions  :   If  optional  questions are  given, the  same  pupils  may not  attempt  the same 
items on a second administration, thereby the reliability of the test is reduced. 

8.5 ITEM ANALYSIS : 

    Item analysis begins after the test is over.  The responses of the examinees are to be analysed to 
check  the  effectiveness  of  the  test  items.    The  teacher  must  come  to  some  judgments  regarding  the 
difficulty level, discriminating power and content validity of items.  Only those items which are effective 
are to be retained, while those which are not should either be discarded or improved.  This is known as 
the process of item‐analysis. 

    A  test  should  be  neither  too  easy  nor  too  difficult;  and  each  item  should  discriminate  validity 
among the high and low achieving students. 

(i)  The difficulty value of each item. 

(ii)  The discriminating power of each item. 

(iii)  The effectiveness of distracters in the given item. 

8.6 STEPS INVOLVED IN ITEM – ANALYSIS : 
 

(i)  Arrange the response sheets from the highest score the lowest score. 
(ii)  From the ordered set of response sheets, make two groups.  Put those with the highest scores in 
one  group  (top  27%)  and  those  with  the  lowest  scores  (lowest  27%)  in  the  order  group.    The 
responses of the respondents in the middle 46% of the group are not included in the analysis. 

(iii)  For  each  item  (T/F,  completion  types)  count  the  number  of  respondents  in  each  group  who 
answered the item correctly.  For alternate response type of items, count the number of students in 
each group who choose each alternate. 

A]  Estimating Item Difficulty : 

    The difficulty of a test is indicated by the percentage of pupils who get the item right  

R 100
Difficulty = ×  
N 1

R – number of pupils who answered the item correctly 

N – total number of pupils who attempted the item. 

  Item 1  Item 2  Item 3  Item 4  Item 5 

D. index  0.375  0.75  0.50  0.15  0.60 

    The higher the difficulty index, the easier the item.  If an item is too difficult, it cannot discriminate 
at all and adds nothing to test reliability or validity.  An item having 0% or 100% difficulty index has no 
discriminating value, Half of the items may have difficulty indices between 25% and 75%.  One‐fourth of 
the  items  should  have  a  diificulty  index  greater  than 0,75  and  one‐fourth of  the  items should  have  a 
diificulty index less than 0.25.. 

B]  Estimating Discrimination Index : 

    The discriminating power of a tool item refers to the degree to which it discriminates between the 
bright and the dull pupils in a group. 

 
    An estimate of an item’s discriminating power can be obtained by the formula: 

Ru – RL
Discriminating power =   
1 N
2

 Ru – Number of correct responses from upper group. 

 RL – Number of correct responses from lower group. 

 N – Total number of pupils who attempted the item. 

    If  all  the  respondents  from  the  upper  and  lower  group  answer  an  item  correctly  or  if  all  fail  to 
answer it correctly, the item has no validity, since in neither case does the item separate the good from 
the poor respondents in the sample. 

    The item has a high discrimination power if the number of high scorers is greater in  the upper 
group as compared to   the number of high scorers in the lower group.  

    Items have zero or negative validity need to be discarded. 

    The higher the discrimination index, the better the item. 

    Thus  the  results  of  item‐analysis  help  one  judge  the  worth  or  quality  of  a  tool  and  also  help  in 
revising the tool items. 

(v)  Standardisation of a Tool :  A tool is said to be standardized if it is constructed according to some 1) 
well  defined  procedure;  2)  administered  according  to  definite  instructions;  3)  scored  according  to  a 
define plan and 4) that it provides a statement of norms. 

    A  tool  is  standardized  in  respect  of  content;  method  of  administration;  method  of  scoring;  and 
setting up of norms. 

    Thus  standardization  is  a  process  for  refining  a  measuring  instrument  through  scientific 
procedures.   

Its steps are as follows : 

1. Preparing a draft form of the tool and writing items as per the operational definition of the tool. 
Items  should  be  selected  in  such  a  way  that  the  expected  respondent  behaviour  in  different 
situations is reflected in the items. 

2.    Computing discrimination index and difficulty index (if it is a test) of the items. In other words, 
conducting item analysis. Through this process, item validity is established. 
 3.    Ascertaining content validity, face validity, construct validity and criterian validity as the case 
may be. 

4.    Ascertaining the reliability of the tool. 

5.    Fixing the time limit. This includes recording the time taken by different individuals at the time 
of the preliminary try out so as to fix the time limit for the final administration of the tool.  It also 
depends upon the purpose of the tool.  Time allowances must always take into consideration the 
age  and  ability  of  the  respondents,  the  type  of  items  used  and  the  complexity  of  the  learning 
outcomes to be measured. 

6.   Writing  the  directions  for  administering  the  tool.    Careful  instructions  for  responding  to 
different  type  of  items  and  for  recording  responses  should  be  given/provided.  The  directions 
should be clear, complete and concise  so that each and every respondent knows what he/she is 
expected to do.  The respondent should be instructed how and where to mark the items, the time 
allowed and  reduction of errors, if any, to be made in scoring.  Instructions for scoring are to be 
given in the test manual. 

7.    Preparing  a  scoring  key.  To  ensure  objectivity  in  scoring,  the  scoring  should  be  done  in  a  pre‐
determined manner. In quantitative research, scoring key is prepared in advance. 

8.    Establishing  norms.  Computing  the  norms  (age‐wise,  gender‐wise,  grade‐wise,  urban‐rural 

location‐wise  and  so  on).  Norms  provide  the  user  of  a  standardized  tool  with  the  basis  for  a 
practical interpretation and application of the results.  A  respondent’s score can be interpreted 
only  by  comparing  it  with  the  scores  obtained  by  similar  respondents.    In  the  process  of 
standardization,  the  tool  must  be  administered  to  a  large,  representative  sample  for  whom  it  is 
designed. 

9.    Preparing  manual  of  the  tool.  Every  standardized  tool  should  be  accompanied  by  the  tool 
manual.  The purpose of the manual is to explain what the tool is supposed to measure, how it 
was  constructed,  how  it  should  be  administered  and  scored  and  how  the  results  should  be 
interpreted  and  used.    It  should  also  explain  the  nature  of  the  sample  selected,  the  number  of 
cases  in  the  sample  and  the  procedure  of  obtaining  the  norms.    The  manual  should  display  the 
weaknesses as well as the strengths of the tool and should provide examples of ways in which the 
tool can be used as well as warnings concerning limitations and possible misuse of the results. 
 

Suggested Readings 

1. Best, J. and Kahn, J. Research in Education (9 ed), New Delhi: Prentice Hall of India Pvt. Ltd. 2006.

2. Campbell, D. T. and Fiske, D. W. “Convergent and Discriminant Validation by the Multitrait-

Multimethod Matrix”. Psychological Bulletin. 56. pp. 81-105.

3. Garret, H. E. Statistics in Psychology and Education. New York: Longmans Green and Co. 5th edition
1958.
 9

TOOLS OF RESEARCH

Unit Structure :

9.0 Objectives
9.1 Introduction
9.2 Rating scale
9.3 Attitude scale
9.4 Opinionnaire
9.5 Questionnaire
9.6 Checklist
9.7 Semantic Differentiate scale
9.8 Psychological Test
9.9 Inventory
9.10 Observation
9.11 Interview
9.12 Let us sum up

9.0 OBJECTIVES :

After reading this unit you will be able to :

• State different types of tools and techniques used for data collection
• Distinguish the basic difference between tools and techniques.
• Describe concept, purpose and uses of various tools and techniques in research.
• State the tools coming under enquiry form, psychological test observation and Interview.

9.1 INTRODUCTION :

In the last chapter, you have studied about how to prepare a research tool. In this chapter we will
study what are those research tools, their concepts and uses in collection of data.
 In every research work, if is essential to collect factual material or data unknown or untapped so far.
They can be obtained from many sources, direct or indirect. It is necessary to adopt a systematic
procedure to collect essential data. Relevant data, adequate in quantity and quality should be collected.
They should be sufficient, reliable and valid.

For checking new, unknown data required for the study of any problem you may use various
devices, instruments, apparatus and appliances. For each and every type of research we need certain
instruments to gather new facts or to explore new fields. The instruments thus employed as means for
collecting data are called tools.

The selection of suitable instruments or tools is of vital importance for successful research.
Different tools are suitable for collecting various kinds of information for various purposes. The research
worker may use one or more of the tools in combination for his purpose. Research students should
therefore familiarise themselves with the varities of tools with their nature, merits and limitations. They
should also know how to construct and use them effectively. The systematic way and procedure by which
a complex or scientific task is accomplished is known as the technique. Techniques is the practical
method, skill or art applied to a particulate task. So, as a researcher we should aware of both the tools and
techniques of research.

The major tools of research in education can be classified broadly into the following categories.

A. Inquiry forms

Questionnaire

Checklist

Score-card

Schedule

Rating Scale

Opinionnaire

Attitude Scale

B. Observation

C. Interview

D. Sociometry

E. Psychological Tests

Achievement Test
 Aptitude Test

Intelligence Test

Interest inventory

Personality measures etc.

In this unit we will discuss some of the tools of each categories.

9.2 RATING SCALE :

Rating scale is one of the enquiry form. Form is a term applied to expression or judgment regarding
some situation, object or character. Opinions are usually expressed on a scale of values. Rating
techniques are devices by which such judgments may be quantified. Rating scale is a very useful device in
assessing quality, specially when quality is difficult to measure objectively. For Example, “How good was
the performance?” is a question which can hardly be answered objectively.

Rating scales record judgment or opinions and indicates the degree or amount of different degrees
of quality which are arranged along a line is the scale. For example: How good was the performance?

Excellent Very good Good Average Below average Poor Very poor

___|________|_______|_____|_________|_________|_____|____

This is the must commonly used instrument for making appraisals. It has a large variety of forms
and uses. Typically, they direct attention to a number of aspects or traits of the thing to be rated and
provide a scale for assigning values to each of the aspects selected. They try to measure the nature or
degree of certain aspects or characteristics of a person or phenomenon through the use of a series of
numbers, qualitative terms or verbal descriptions.

Ratings can be obtained through one of three major approaches:

• Paired comparison
• Ranking and
• Rating scales
The first attempt at rating personality characteristics was the man to man technique devised curing
World-war-I. This technique calls for a panel of raters to rate every individual in comparison to a standard
person. This is known as the paired comparison approach.
 In the ranking approach every single individual in a group is compared with every other individual
and to arrange the judgment in the form of a scale.

In the rating scale approach which is the more common and practical method rating is based on the
rating scales, a procedure which consists of assigning to each trait being rated a scale value giving a valid
estimate of its status and then comparing the separate ratings into an over all score.

Purpose of Rating Scale:

Rating scales have been successfully utilized for measuring the following:

• Teacher Performance/Effectiveness
• Personality, anxiety, stress, emotional intelligence etc.
• School appraisal including appraisal of courses, practices and programmes.

Useful hints on Construction of Rating Scale:

A rating scale includes three factors like:

i) The subjects or the phenomena to be rated.

ii) The continuum along which they will be rated and

iii) The judges who will do the rating.

All taken three factors should be carefully taken care by you when you construct the rating scale.

1) The subjects or phenomena to be rated are usually a limited number of aspects of a thing or of a traits
of a person. Only the most significant aspects for the purpose of the study should be chosen. The
usual may to get judgement is on five to seven point scales as we have already discussed.

2) The rating scale is always composed of two parts:

i) An instruction which names the subject and defines the continuum and

ii) A scale which defines the points to be used in rating.

3) Any one can serve as a rater where non-technical opinions, likes and dislikes and matters of easy
observation are to be rated. But only well informed and experienced persons should be selected for
rating where technical competence is required. Therefore, you should select experts in the field as rater
 or a person who form a sample of the population in which the scale will subsequently be applied.
Pooled judgements increase the reliability of any rating scale. So employ several judges, depending on
the rating situation to obtain desirable reliability.

Use of Rating Scale :

Rating scales are used for testing the validity of many objective instruments like paper pencil
inventories of personality. They are also advantages in the following fields like :

• Helpful in writing reports to parents

• Helpful in filling out admission blanks for colleges
• Helpful in finding out student needs
• Making recommendations to employers.
• Supplementing other sources of understanding about the child
• Stimulating effect upon the individuals who are rated.

Limitations of Rating Scale :

The rating scales suffer from many errors and limitations like the following:

As you know that the raters would not like to run down their own people by giving them low
ratings. So in that case they give high ratings to almost all cases. Sometimes also the raters are included
to be unduly generous in rating aspects which they had to opportunity to observe. It the raters rate in
higher side due to those factors, then it is called as the generosity error of rating.

The Errors of Central Tendency :

Some observes wants to keep them in safe position. Therefore, they rate near the midpoint of the
scale. They rate almost all as average.

Stringency Error :

Stringency error is just the opposite of generosity of error. These types of raters are very strict,
cautions and hesitant in rating in average and higher side. They have a tendency to rate all individuals
low.

The Hallo Error :

 When a rater rates one aspect influenced by other is called hallo effect. For if a person will be rated
in higher side on his achievement because of his punctually or sincerely irrespective of his perfect answer
it called as hallo effect. The biased-ness of the rater affects from one quality to other.

The Logical Error :

It is difficult to convey to the rater just what quality one wishes him to evaluate. An adjective or
Adverb may have no universal meaning. It the terms are not properly understood by the rater and he rates,
then it is called as the logical error. Therefore, brief behavioural statements having clear objectives should
be used.

Check Your Progress - I

Q.1 What is rating scale?

Q.2 What are the approaches of rating?

Q.3 Explain the various purposes of rating scale?

Q.4 What are the factors to be considered during construction of rating scale?

Q.5 What is rating scale? Explain it’s uses.

Q.6 Write short notes on:

i) The Generosity Error

ii) The Logical Error

iii) The Hallo error

iv) Stringency error

v) The errors of central Tendency

9.3 ATTITUDE SCALE :

Attitude scale is a form of appraisal procedure and it is also one of the enquiry term. Attitude scales
have been designed to measure attitude of a subject of group of subjects towards issues, institutions and
group of peoples.

The term attitude is defined in various ways, “the behaviour which we define as attitudinal or
attitude is a certain observable set” organism or relative tendency preparatory to and indicative of more
complete adjustment.”

- L. L. Bernard

“An attitude may be defined as a learned emotional response set for or against something.”

- Barr David Johnson

An attitude is spoken of as a tendency of an individual to read in a certain way towards a

Phenomenon. It is what a person feels or believes in. It is the inner feeling of an individual. It may be
positive, negative or neutral.

Opinion and attitude are used sometimes in a synonymous manner but there is a difference between
two. You will be able to know when we will discuss about opinionnaire. An opinion may not lead to any
kind of activity in a particular direction. But an attitude compels one to act either favourably or
unfavourably according to what they perceive to be correct. We can evaluate attitude through
questionnaire. But it is ill adapted for scaling accurately the intensity of an attitude. Therefore, Attitude
scale is essential as it attempts to minimise the difficulty of opinionnaire and questionnaire by defining the
attitude in terms of a single attitude object. All items, therefore, may be constructed with graduations of
favour or disfavour.
Purpose of Attitude Scale :

In educational research, these scales are used especially for finding the attitudes of persons on
different issues like:

• Co-education
• Religious education
• Corporal punishment
• Democracy in schools
• Linguistic prejudices
• International co-operation etc.

Characteristics of Attitude Scale :

Attitude scale should have the following characteristics.

• It provides for quantitative measure on a unidimensional scale of continuum.

• It uses statements from the extreme positive to extreme negative position.
• It generally uses a five point scale as we have discussed in rating scale.
• It could be standardised and norms are worked out.
• It disguises the attitude object rather than directly asking about the attitude on the subject.
Examples of Some Attitude Scale :

Two popular and useful methods of measuring attitudes indirectly, commonly used for research purposes
are:

• Thurstone Techniques of scaled values.

• Likert’s method of summated ratings.

Thurstone Technique :

Thurstone Technique is used when attitude is accepted as a uni-dimensional linear Continuum. The
procedure is simple. A large number of statements of various shades of favourable and unfavourable
opinion on slips of paper, which a large number of judges exercising complete detachment sort out into
eleven plies ranging from the most hostile statements to the most favourable ones. The opinions are
carefully worded so as to be clear and unequivocal. The judges are asked not express tier opinion but to
sort them at their face value. The items which bring out a marked disagreement between the judges un
assigning a position are discarded. Tabulations are made which indicate the number of judges who placed
each item in each category. The next step consists of calculating cumulated proportions for each item and
ogives are constructed. Scale values of each item are read from the ogives, the values of each item being
that point along the baseline in terms of scale value units above and below which 50% of the judges placed
the item. It we’ll be the median of the frequency distribution in which the score ranges from 0 to 11.

The respondent is to give his reaction to each statement by endorsing or rejecting it. The median
values of the statements that he checks establishes his score, or quantifies his opinion. He wins a score as
an average of the sum of the values of the statements he endores.

Thurstone technique is also known as the technique equal appearing intervals.

Sample Items From Thurstone Type Scales :

Scaled
Statement
value

I think this company treats its employees 10.4

Better than any other company does. 9.5

It I had to do it over again I’d still work for this 5.1

company.

The workers put as much over on the company as the 2.1

company puts over on them.

You have got to have pull with certain people around 0.8
here to get ahead. An honest man fails in this company.

The Likert Scale :

The Likert scale uses items worded for or against the proposition, with five point rating response
indicating the strength of the respondent’s approval or disapproval of the statement. This method removes
the necessity of submitting items to the judges for working out scaled values for each item. It yields scores
very similar to those obtained from the Thurstone scale. It is an important over the Thurstone method.

The first step is the collection of a member of statements about the subject in question. Statements
may or may not be correct but they must be representative of opinion held by a substantial number of
people. They must express definite favourableness or unfavourableness to a particular point of view. The
number of favourable and unfavourable statements should be approximately equal. A trial test maybe
administered to a number of subjects. Only those items that correlate with the total test should be retained.
 The Likerts calling techniques assigns a scale value to each of the five responses. All favourable
statements are scored from maximum to minimum i. e. from a score of 5 to a score of one or 5 for strongly
agree and so on 1 for strongly disagree. The negative statement or statement apposing the proposition
would be scored in the opposite order . e. from a score of 1 to a score of 5 or 1 for strongly agree and so on
5 for strongly disagree.

The total of these scores on all the items measures a respondent’s favourableness towards the
subject in question. It a scale consists of 30 items, Say, the following score values will be of interest.

30 × 5 = 150 Most favourable response possible

30 × 3 = 90 A neutral attitude

30 × 1= 30 Most unfavourable attitude

It is thus known as a method of summated ratings. The summed up score of any individual would
fall between 30 and 150. scores above 50 will indicate a favourable and scores below go an unfavourable
attitude.

Sample Items from Linkert Type Minnesota

Scale on Morale

Responses Items

SA A U D SD Times are getting better

SA A U D SD Any man with ability and willingness to work

hard has a good chance of being successful.

SA A U D SD Life is just a series of disappointments.

SA A U D SD It is great to be living in those exciting times.

SA A U D SD Success is more dependent on lack than on

real ability.

Limitations Of Attitude Scale :

In the attitude scale the following limitations may occur:

• An individual may express socially acceptable opinion conceal his real attitude.
• An individual may not be a good judge of himself and may not be clearly aware of his real attitude.
• He may not have been controlled with a real situation to discover what his real attitude towards a
specific phenomenon was.
• There is no basis for believing that the five positions indicated in the Likert’s scale are equally spaced.
• It is unlikely that the statements are of equal value in ‘forness’ or “againstness”.
• It is doubtful whether equal scores obtained by several individuals would indicate equal favourableness
towards again position.
• It is unlikely that a respondent can validity react to a short statement on a printed form in the absence of
real like qualifying Situation.
• In sprite of anonymity of response, Individuals tend to respond according to what they should feel
rather than what they really feel.

However, until more precise measures are developed, attitude scale remains the best device for the
purpose of measuring attitudes and beliefs in social research.

Check Your Progress – II

Q.1 What is attitude scale? Explain it’s purpose and Characteristics.

Q.2 What is attitude scale? Explain the methods of measuring attitudes in research.
Q.3 Define attitude. Explain Likerts scale to measure attitude.

9.4 OPINIONNAIRE :

“Opinion polling or opinion gauging represents a single question approach. The answers are
usually in the form of ‘yes’ or ‘no’. An undecided category is often included. Sometimes large number of
response alternatives if provided.”

- Anna Anastusi

The terms opinion and attitude are not synonymous, through sometimes we used it synonymously.
We have till now discussed that attitudes scale. We have also discussed that attitudes are impressed
opinions. You can now understand the difference between opinionnaire and attitude scale, when we
discuss of out opinionnaire, it is characteristics and purposes.

Opinion is what a person says on certain aspects of the issue under considerations. It is an outward
expression of an attitude held by an individual. Attitudes of an individual can be inferred or estimated
from his statements of opinions.

An opinionnaire is defined as a special form of inquiry. It is used by the researcher to collect the
opinions of a sample of population on certain facts or factors the problem under investigation. These
opinions on different facts of the problem under study are further quantified, analysed and interpreted.

Purpose :

Opinionnaire are usually used in researches of the descriptive type which demands survey of
opinions of the concerned individuals. Public opinion research is an example of opinion survey. Opinion
polling enables the researcher to forecast the coming happenings in successful manner.

Characteristics :
• The opinionnaire makes use of statements or questions on different aspects of the problem under
investigation.
• Responses are expected either on three point or five point scales.
• It uses favourable or unfavourable statements.
• It may be sub-divided into sections.
• The gally poll ballots generally make use of questions instead of statements.
• The public opinion polls generally rely on personal contacts rather than mail ballots.
Sample Items of Opinionnaire :

The following statements are from the opinionnaire on the reforms in educational administration
introduced in A. P. during 1956-66.

1) Democratic decentralization has helped to develop

democratic values and practices in rural people.
A U D

2) There has been consequent improvements of

educational standards.

3) Specified subject inspectorate is better than Panel A U D

type of inspectorate.

4) Inspection stripped of Administrative powers does

not help much. A U D

5) Primary education should be brought under a

separate directorate as was done in some status.

A U D

A U D

9.5 QUESTIONNAIRE :

A questionnaire is a form prepared and distributed to secure responses to certain questions. It is a

device for securing answers to questions by using a form which the respondent fills by himself. It is a
systematic compilation of questions that are submitted to a sampling of population from which information
is desired.

Questionnaire rely on written information supplied directly by people in response to questions. The
information from questionnaires tends to fall into two broad categories – ‘facts’ and ‘opinions’. It is worth
stressing that, in practice, questionnaires are very likely to include questions about both facts and opinions.

Purpose :

The purpose of the questionnaire is to gather information from widely scattered sources. It is
mostly used in uses in cases where one can not readily see personally all of the people from whom he
desires responses. It is also used where there is no particular reason to see them personality.

Types :

Questionnaire can be of various type on the basis of it’s preparation. They are like:

• Structured v/s Non Structured

• Closed v/s Open
• Fact v/s Opinion

Structured v/s Non-Structured Questionnaire :

The structured questionnaire contains definite, concrete and directed questions, where as non-
structured questionnaire is often used in interview and guide. It may consist of partially completed
questions.

Closed v/s Open Questionnaire :

The question that call for short check responses are known as restricted or closed form type. For
Example, they provide for marking a yes or no, a short response or checking an item from a list of
responses. Here the respondent is not free to wrote of his own, he was to select from the selected from the
supplied responses. On the other hand, increase of open ended questionnaire, the respondent is free to
response in his own words. Many questionnaire also included both close and open type questions. The
researcher selects the type of questionnaire according to his need of the study.
Fact and Opinion :

Incase of fact questionnaire, the respondent is expected to give information of facts without any
reference to his opinion or attitude about them.

But incase of opinion questionnaire the respondent gives the information about the facts with his
own opinion and attitude.

Planning the Use of Questionnaire :

The successful use of questionnaire depends on devoting the right balance of effort to the planning
stage, rather than rushing too early into administering the questionnaire. Therefore, the researcher should
have a clear plan of action in mind and costs, production, organization, time schedule and permission
should be taken care in the beginning. When designing a questionnaire, the characteristics of a good
questionnaire should be kept in mind.

Characteristics of A Good Questionnaire :

• Questionnaire should deal with important or significant topic to create interest among respondents.
• It should seek only that data which can not be obtained from other sources.
• It should be as short as possible but should be comprehensive.
• It should be attractive.
• Directions should be clear and complete.
• It should be represented in good Psychological order proceeding from general to more specific
responses.
• Double negatives in questions should be avoided.
• Putting two questions in one question also should be avoided.
• It should avoid annoying or embarrassing questions.
• It should be designed to collect information which can be used subsequently as data for analysis.
• It should consist of a written list of questions.
• The questionnaire should also be used appropriately.

When is it appropriate to use a questionnaire for research?

Different methods are better suited to different circumstances and questionnaire are no exception to
it. Questionnaire are used at their most productive:

• When used with large numbers of respondents.

• When what is required tends to be fairly straight forward information.
• When there is a need for standardize data from indentical information.
• When time is allows for delays.
• When resources allow for the cast of printing and postage.
• When respondents can be expected to be able to read and understand the questions.

Designs of Questionnaire :

After construction of questions on the basis of it’s characteristics it should be designed with some
essential routines like:

• Background information about the questionnaire.

• Instructions to the respondent.
• The allocation of serial numbers and
• Coding Boxes.

Background Information about The Questionnaire

Both from ethical and practical point of view, the researcher needs to provide sufficient background
information about the research and the questionnaire. Each questionnaires should have a cover page, on
which some information appears about:

• The sponsor
• The purpose
• Return address and date
• Confidentiality
• Voluntary responses and
• Thanks

Instructions to the Respondent :

It is very important that respondents are instructed to go presented at the start of the questionnaire
which indicate what is expected from the respondents. Specific instructions should be given for each
question where the style of questions varies through out the questionnaire. For Example – Put a tick mark
in the appropriate box and circle the relevant number etc.

The Allocation of Serial Numbers :

 Whether dealing with small or large numbers, a good researcher needs to keep good records. Each
questionnaire therefore should be numbered.

Advantages of Questionnaire :

Questionnaire are economical. In terms of materials, money and time it can supply a considerable
amount of research data.

• It is easier to arrange.
• It supplies standardized answers
• It encourages pre-coded answers.
• It permits wide coverage.
• It helps in conducting depth study.

Disadvantages :

• It is reliable and valid, but slow.

• Pre-coding questions can deter them from answering.
• Pre-coded questions can bias the findings towards the researcher.
• Postal questionnaire offer little opportunities to check the truthfulness of the answers.
• It can not be used with illiterate and small children.

Irrespective of the limitations general consensus goes in favour of the use of questionnaire. It’s
quality should be improved and we should be restricted to the situations for which it is suited.

Check Your Progress – III

Q.1 Distinguish between opinionnaire and questionnaire.

Q.2 Write short notes on:

(a) Closed and open questionnaire.

 (b) Structured and Non-Structure questionnaire.

(c) Fact and Opinion.

The serial number helps to distinguish and locate if necessary. It can also helps to identify the date
of distribution, the place and possibility the person.

Coding Boxes :

When designing the questionnaire , it is necessary to prevent later complications which might arise
at the coding stage. Therefore, you should note the following points:

• Locate coding boxes neatly on the right hand side of the page.
• Allow one coding box for each answer.
• Identify each column in the complete data file underneath the appropriate coding box in the
questionnaire.

Besides these, the researcher should also be very careful about the length and appearance of the
questionnaire, wording of the questions, order and types of questions while constructing a questionnaire.

Criteria of Evaluating a Questionnaire :

You can evaluate your questionnaire whether it is a standard questionnaire or not on the basis of the
following criteria:

• It should provide full information pertaining to the area of research.

• It should provide accurate information.
• It should have a decent response rate.
• It should adopt an ethical stance and
• It should be feasible.

Like all the tools, it also has some advantages and disadvantages based on it’s uses.

9.6 CHECKLIST :

A checklist, is a type of informational job aid used to reduce failure by compensating for potential
limits of human memory and attention. It helps to ensure consisting and completeness in carrying out a
task. A basic example is ‘to do list’. A more advanced checklist which lays out tasks to be done according
to time of a day or other factors.

The checklist consists of a list of items with a place to check, or to mark yes or no.

Purpose :

The main purpose of checklist is to call attention to various aspects of an object or situation, to see
that nothing of importance is overlooked. For Example, if you have to go for outing for a week, you have
to list what things you have to take with you. Before leaving home, if you will check your baggage with
the least there will be less chance of forgetting to take any important things, like toothbrush etc. it ensures
the completeness of details of the data. Responses to the checklist items are largely a matter of fact, not of
judgment. It is an important tool in gathering facts for educational surveys.

Uses :

Checklists are used for various purposes. As we have discussed that we can check our requirements
for journey, Birthday list, proforma for pass-port, submitting examination form or admission form etc. in
every case, it we will check before doing the work, then there is less chance of overlooking any, important
things. As it is useful in over daily life, it is also useful in educational field in the following way.

• To collect acts for educational surveys.

• To record behaviour in observational studies.
• To use in educational appraisal, studies – of school buildings, property, plan, textbooks, instructional
procedures and outcomes etc.
• To rate the personality.
• To know the interest of the subjects also. Kuder’s interest inventory and Strong’s Interest Blank are
also checklists.
Hints on Constructing Checklist :

• Items in the checklist may be continuous or divided into groups of related items.
• Items should be arranged in categories and the categories in a logical or psychological order.
• Terms used in the items should be clearly defined.
• Checklist should be continuous and comprehensive in nature.
• A pilot study should be taken to make it standardized.
• Checklist can be constructed in four different ways by arranging items differently.
(1) In one of the arrangement all items found in a situation are to be checked. For Example, a subject may
be asked to check ( ) in the blank side of each activity undertaken in a school.

(2) In the second form, the respondent is asked to check with a ‘yes’ or ‘no’ or asked to encircle or
underline the response to the given item. For Example, (1) Does your school have a house system?
Yes/No

(3) In this form, all the items are positive statements with checks ( ) to be marked in a column of a right.
For Example, (1) The school functions as a community centre ( ).

(4) The periodical tests are held – fortnightly, monthly, quarterly, regularly.

The investigator has to select any one of the format appropriate to his problem and queries or the
combination of many as it requires.

Analysis and Interpretation of Checklist Data :

The tabulation and quantification of checklist data is done from the responses. Frequencies are
counted, percentages and averages calculated, central tendencies, measures of variability and co-efficient
of correlation completed as and when necessary. In long checklists, where related items are grouped
together category wise, the checks are added up to give total scores for the category wise total scores can
be compared between themselves or with similar scores secured through other studies.

The conclusions from checklist data should be arrived at carefully ad judiciously keeping in view
the limitations of the tools and respondents.
Merits :

• Students can measure their own behaviour with the help of checklist.
• Easy and simple to use and frame the tools.
• Wanted and unwanted behaviours can be included.
• Personal - Social development can be checked.

Limitations :

• Only the presence or absence of the ability can be tested.

• Yes or no type judgement can only be given.
• How much can not be tested through checklist.
For Example, you want to test the story telling still of a student. You can check only whether the
student developed or not developed the skill but you can not study how much he has developed?

When we want to check ‘yes’ or ‘no’ of any ability, checklist is used.

Check Your Progress - IV

Q.1 Prepare a checklist for any skill.

9.7 SEMANTIC DIFFERENTIAL SCALE:

Semantic differential is a type of a rating scale designed to measure the connotative meaning of
objects, events and concepts. The connotations are used to drive the attitude towards the given object,
event of concept.
Semantic Differential:

sweet bitter
falt unfalt
warm cold
beautiful ugly
meaningful meaningless
brave cowardly
bright dark

Fig. 1 Modem Japanese version of the semantic Differential.

The Kanji characters in background stand for “God” and “Wind” respectively, with the compound
reading “Kamikaze”. (Adapted from Dimensions of Meaning. Visual Statistics Illustrated at
VisualStatistics.net.)

Osgood’s semantic differential was designed to measure the connotative meaning of concepts. The
respondent is asked to choose where his or her position lies, on a scale between two bipolar adjectives (for
example: “Adequate-Inadequate”, “Good-Evil” or “Valuable-Worthless”). Semantic differentials can be
used to describe not only persons, but also the connotative meaning of abstract concepts - a capacity used
extensively in effect control theory.

Theoretical Background

Nominalists and Realists :

Theoretical underpinnings of Charles E. Osgood’s semantic differential have roots in the medieval
controversy between then nominalists and realists. Nominalists asserted that only real things are entities
and that abstractions from these entities, called universals, are mere words. The realists held that
universals have an independent objective existence either in a realm of their own or in the mind of God.
Osgood’s theoretical work also bears affinity to linguistics and general semantics and relates to
Korzybski’s structural differential.

Use of Adjectives :
 The development of this instrument provides an interesting insight into the border area between
linguistics and psychology. People have been describing each other since they developed the ability to
speak. Most adjectives can also be used as personality descriptors. The occurrence of thousands of
adjectives in English is an attestation a of the subtleties in descriptions of persons and their behaviour
available to speakers of English. Roget’s Thesaurus is an early attempt to classify most adjectives into
categories and was used within this context to reduce the number of adjectives to manageable subsets,
suitable for factor analysis.

Evaluation, Potency and Activity :

Osgood and his colleagues performed a factor analysis of large collections of semantic differential
scales and found three recurring attitudes that people use to evaluate words and phrases: valuation,
potency, and activity. Evaluation loads highest on the adjective pair ‘active-passive’ defines the activity
factor. These three dimensions off affective meaning were found to be cross-cultural universals in a study
of dozens of cultures.

This factorial structure makes intuitive sense. When our ancestors encountered a person, the initial
perception had to be whether that person represents a danger. Is the person good or bad? Next, is the
person strong or weak? Our reactions to a person markedly differ it perceived as good and strong, good
and weak, bad and weak, or bad and strong. Subsequently, we might extend our initial classification to
include cases of persons who actively threaten us or represent only a potential, danger, and so on. The
evaluation, potency and activity factors thus encompass a detailed descriptive system of personality.
Osgood’s semantic differential measures these three factors. It contains sets of adjective pairs such as
warm-cold, bright-dark, beautiful-ugly, sweet-bitter, fair-unfair, brave-cowardly, meaningful-meaningless.

The studies of Osgood and his colleagues revealed that the evaluate factor accounted for most of the
variance in scalings, and related this to the idea of attitudes.

Usage :

The semantic differential is today one of the most widely used scales used in the measurement of
attitudes. One of the reasons is the versatility of the items. The bipolar adjective pairs can be used for a
wide variety of subjects, and as such the scale is nicknamed “the ever ready battery” of the attitude
researcher.

A. Semantic Differential Scale :

This is a seven point scale and the end points of the scale are associated with bipolar labels.
 1 7

Unpleasant 2 3 4 5 6 Pleasant
Submissive Dominant

Suppose we want to know personality of a particular person. We have options –

a. Unpleasant / Submissive

b. Pleasant / Dominant

Bi-polar means two opposite streams. Individual can score between 1 to 7 or 3 to 3. On the basis
of these responses profiles are made. We can analyse for two for three products and by joining these
profiles we get profile analysis. It could take any shape depending on the number of variables.

Profile Analysis
----------------/-------------

-----------/------------------

-------/----------------------

Mean and median are used for comparison. This scale helps to determine overall similarities and
differences among objects.

When Semantic Differential Scale is used to develop an image profile, it provides a good basis for
comparing images of two or more items. The big advantage of this scale is its simplicity, while producing
results compared with those of the more complex scaling methods. The method is easy and fast to
administer, but it is also sensitive to small differences in attitude, highly versatile, reliable and generally
valid.

Statistical Properties :

Five items, or 5 bipolar pairs of adjectives, have been proven to yield reliable findings, which
highly correlate with alternative measures of the same attitude.

The biggest problem with his scale is that the properties of the level of measurement are unknown.
The most statistically should approach is to treat it as an ordinal scale, but it can be argued that the neutral
response (i. e. the middle alternative on the scale) serves as an arbitrary zero point, and that the intervals
between the scale values can be treated as equal, making it an interval scale.
 A detailed presentation on the development of the semantic differential is provided in the
monumental book, Cross-Cultural Universals of Affective Meaning. David R. Heise’s Surveying Cultures
provides a contemporary update with special attention to measurement issues when using computerized
graphic rating scales.

9.8 PSYCHOLOGICAL TESTS:

Among the most useful and most frequently employed tools of educational research psychological
tests occupy a very significant position. Psychological tests are described to describe and measure a
sample of certain aspects of human behaviour or inner qualities. They yield objective descriptions of some
psychological aspects of an individual’s personality and translate them in quantitative terms. As we have
mentioned earlier there are various kinds of psychological tests. In this unit we will discuss ‘Aptitude
tests’ and ‘Inventories’.

Aptitude Tests :

“Aptitude tests attempt to predict the capacities or the degree of achievement that may be expected
from individuals in a particular activity”.

Aptitude is a means by which one can find the relative knowledge of a person in terms of his
intelligence and also his knowledge in general.

Purpose :

The purpose of aptitude test is to test a candidate’s profile. Aptitude test helps to check one’s
knowledge and filters the good candidates. The ability of creativity and intelligence is proved by the
aptitude test. It always checks the intelligence and fastness of the person in performance.

Importance of Aptitude Test :

Research data show that individually administered aptitude tests have the following qualities:

• They are excellent predictors of future scholastic achievement.

• They provide ways for comparison of a child’s performance with other in a same situation.
• They provide a profile of strength and weaknesses.
• They asses difference among individuals.
Uses Of Aptitude Test :

Aptitude tests are valuable in making programme and curricula decisions. In general they have
three major uses:

Instructional : Teacher can use aptitude test results to adopt their curricula to match the level of students
or to design assignments for students who differ widely.

Administrative : Result of Aptitude tests help in determining the programmes for college on the basis of
aptitude level of high-school. It can also be identify students to be accelerated or given extra attention, for
exampling and in predicting job training performance.

Guidance : result of aptitude tests help counsellors to help parents and students. Parents develop realistic
expectations for their Child’s performance and students understand their own strength and weaknesses.

Intelligence tests are also a kind of aptitude test as they describe and measure the general ability
which enters into the performance of every activity and thus predict the degree of achievement that may be
expected from individuals in various activities.

Aptitude test, however have proved of great value for research in educational and vocational
guidance, for research in selection of candidates for particular course of study or professional training and
for research of the complex causal relationship type.

9.9 INVENTORY :

Inventory is a list, record or catalog containing list of traits, preferences, attitudes, interests or
abilities used to evaluate personal characteristics or skills.

The purpose of inventory is to make a list about a specific trait, activity or programme and to check
to what extent the presence of that ability types of Inventories like

• Internet Inventory and

• Personality Inventory

Interest Inventory :
 Persons differ in their interests, likes and dislikes. Internets are significant element in the
personality pattern of individuals and play an important role in their educational and professional careers.
The tools used for describing and measuring interests of individuals are the internet inventories or interest
blanks. They are self report instruments in which the individuals note their own likes and dislikes. They
are of the nature of standardised interviews in which the subject gives an introspective report of his
feelings about certain situations and phenomena which is then interpreted in terms of internets.

The use of interest inventories is most frequent in the areas of educational and vocational guidance
and case studies. Distinctive patterns of interest that go with success have been discovered through
research in a number of educational and vocational fields. Mechanical, computational, scientific, artifice,
literary, musical, social service, clerical and many other areas of interest have been analysed informs of
activities. In terms of specific activities, a person’s likes and dislikes are sorted into various interest areas
and percentile scores calculated for each area. The area where a person’s percentile scores are relatively
higher is considered to be the area of his greatest interests, the area in which he would be the happiest and
the most successful.

As a part of educational surveys of many kinds, children’s interest in reading, in games, in

dramatics, in other extracurricular activities and in curricular work etc. are studied.

One kind of instrument, most commonly used in interest measurement is known as Strong’s
Vocational Interest Inventory. It compares the subject’s pattern of interest to the interest patterns of
successful individuals in a number of vocational fields. This inventory consists of the 400 different items.
The subject has to tick mark one of the alternatives i. e. L(for like), I(indifference) or D(Dislike) provided
against each item. When the inventory is standardised, the scoring keys and percentile norms are prepared
on the basis of the responses of a fairly large number of successful individuals of a particular vocation. A
separate scoring key is therefore prepared for each separate vocation or subject area. The subject’s
responses are scored with the scoring key of a particular vocation in order to know his interest or lack of
interest or lack of interest in the vocation concerned. Similarly his responses can be scored with scoring
keys standardised for other vocational areas. In this way you can determine one’s areas of vocational
interest. Another well known interest inventories, there are also personality inventories to measure the
personality. You can prepare inventories of any ability to measure it.

Check Your Progress – V

Q.1 What are psychological tests? Explain the use of aptitude test as a tool of research.
Q.2 What are inventories? Explain it’s role in research with example.

9.10 OBSERVATION :

Observation offers the researcher a distinct way of collecting data. It does not rely on what people
say they do, or what they say they think. It is more direct than that. Instead, it draws on the direct
evidence of the eye to witness events first hand. It is a more natural way of gathering data. Whenever
direct observation is possible it is the preferable method to use.

Observation method is a technique in which the behaviour of research subjects is watched and
recorded without any direct contact. It involve the systematic recording of observable phenomena or
behaviour in a natural setting.

Purpose :

The purpose of observation techniques are:

• To collect data directly.

• To collect substantial amount of data in short time span.
• To get eye witness first hand data in real like situation.
• To collect data in a natural setting.

Characteristics :
 It is necessary to make a distinction between observation as a scientific tool and the casual
observation of the man in the street. An observation with the following characteristics will be scientific
observation.

• Observation is systematic.
• It is specific.
• It is objective.
• It is quantitative.
• The record of observation should be made immediately.
• Expert observer should observe the situation.
• It’s result can be checked and verified.

Types of Observation :

On the basis of the purpose of observation may be of varied type like:

• Structured and Unstructured

• Participant and Non-participant

Structured and Unstructured Observation :

In the early large stage of an investigation, it is necessary to allow maximum flexibility in

observation to obtain a true picture of the phenomenon as a whole. In the early stage, it we attempt to
restrict the observation to certain areas, then there we’,, be the risk of overlooking some of the more
crucial aspects. As the investigator studies the significant aspects and observes some restricted aspects of
the situation to derive more and rigorous generalizations. So in the first stage of observation, the
observation is wide and unstructured and as the investigation proceeds observation gets restricted and
structured.

Participant and Non-Participant Observation:

In participant observation, the observer becomes more or less one of the groups under observation
and shares the situation as a visiting stranger, an attentive listener, an eager learner or as a complete
participant observer, registering, recording and interpreting behaviour of the group.

In non-participant observation, the observer observes through one way screens and hidden
microphones. The observer remains a look from group. He keeps his observation as inconspicuous as
possible. The purpose of non-participant observation is to observe the behaviour in a natural setting. The
subject will not shift his behaviour or the will not be conscious hat someone is observing his behaviour.
 The advantages and disadvantages of participant and non-participant observation depend largely on
the situation. Participant observation is helpful to study about criminals at least participating with person
sometime. It gives a better in sight into the life. Therefore it has a built in validity test. It’s disadvantages
are that it is time consuming As he develops relationship with the members, there is a chance of lousing
his neutrality, objectivity and accuracy to rate things as they are:

Non-participant observation is used with groups like infants, children or abnormal persons. It
permits the use of recording instruments and the gathering of large quantities of data.

Therefore, some researchers feel that it is best for the observer to remain only a partial participant
and to maintain his status of scientific observer apart from the group.

Steps of Effective Observation:

As a research tool effective observation needs effective

• Planning
• Execution
• Recording and
• Interpretation
Planning:

While planning to employ observation as a research technique the following factors should be taken
into consideration.

• Sample to be observed should be adequate.

• Units of behaviour to be observed should be clearly defined.
• Methods of recording should be simplified.
• Detail instruction should be given to observes if more than one observe is employed to maintain
consistency.
• Too many variables should not be observed simultaneously.
• Excessively long period of observation without rest period should be avoided.
• Observes should be fully trained and well equipped.
• Records of observation must be comprehensive.

Execution :
 A good observation plan lends to success only when followed with skill and expert execution.
Expert execution needs:

• Proper arrangement of special conditions for the subject.

• Assuming the proper physical position for observing.
• Focusing attention on the specific activities or units of behaviour under observation.
• Observing discreetly the length and number of periods and internals decided upon.
• Handling well the recording instruments to be used.
• Utilising the training received in terms of expertness.

Recording:

The two common procedures for recording observations are:

• Simultaneous
• Soon after the observation

Which methods should be used depend on the nature of the group? The type of behaviour to be
observed. Both the method has their merits and limitations. The simultaneous form of recording may
distract the subjects while after observation the observer may distract the subjects while after observation
the observer may fail to record the complete and exact information. Therefore for a systematic collection
of data the various devices of recording should be used. They are like – checklist, rating scale and score
card etc.

Interpretation:

Interpretation can be done directly by the observer at the time of his observation. Where several
observers are involved, the problem of university is there. Therefore, in such instances, the observer
merely records his observations and leaves the matter of interpretation to an export that is more likely to
provide a unified frame of reference. It must of course, be recognized that the interpreter’s frame of
reference is fundamental to any interpretation and it might be advisable to insist on agreement between
interpreters of different background.

Limitations of Observation :

• The limitations of observation are:

• Establishing validity is difficult.
• Subjectivity is also there.
• It is a slow and labourious process.
• It is costly both in terms of time of time and money.
• The data may be unmanageable.
• There is possibility of biasness
These limitations can be minimized by systematic observation as it provides a framework for
observation which all observes will use. It has the following advantages.

Advantages of Observation :

• Data collected directly

• Systematic and rigorous
• Substantial amount of data can be collected in a relatively short time span.
• Provides pre-coded data and ready for analysis.
• Inter observer reliability is high.

However, observation is a scientific technique to the extent that it serves a formulated research
purpose, planned systematically rather than occurring haphazardly, systematically recorded and related to
more general propositions and subjected to checks and controls with respect to validity, reliability and
precision.

Check Your Progress – VI

Q.1 Explain the steps of observational techniques with it’s merit’s and limitations.

Q.2 Write short notes on:

(a) Participant and non0participant observation.

(b) Structured and non-structures observation.

9.11 INTERVIEW :

Interviews are an attractive proposition for the project researcher. Interviews are something more
than conversation. They involve a set of assumptions and understandings about the situation which are not
normally associated with a casual conversion. Interviews are also refered as an oral questionnaire by some
people, but it is indeed mush more than that. Questionnaire involves indirect data collection, whereas
Interview data is collected directly from others in face to face contact. As you know, people are hesitant to
wrote something than to talk. With friendly relationship and rapport, the interviewer can obtain certain
types of confidential information which might be reluctant to put in writing.

Therefore research interview should be systematically arranged. It does not happen by chance. The
interviews not done by secret recording of discussions as research data. The consent of the subject is taken
for the purpose of interview. The words of the interviews can be treated as ‘on the record’ and ‘for the
record’. It should not be used for other purposes besides the research purpose. The discussion therefore is
not arbitrary or at the whim of one of the parties. The agenda for the discussion is set by the researcher. It
is dedicated to investigating a given topic.

Importance of Interview :

Whether it is large scale research or small scale research, the nature of the data collection depends
on the amount of resources available. Interview is particularly appropriate when the researcher wishes to
collect data based on:

• Emotions, experiences and feelings.

o Sensitive issues.
o Privileged information.
• It is appropriate when dealing with young children, illiterates, language difficulty and limited,
intelligence.
• It supplies the detail and depth needed to ensure that the questionnaire asks valid questions while
preparing questionnaire.
• It is a follow up to a questionnaire and complement the questionnaire.
• It can be combined with other tools in order to corroborate facts using a different approach.
• It is one of the normative survey methods, but it is also applied in historical, experimental, case studies
.
Types of Interview :
 Interviews vary in purpose, nature and scope. They may be conducted for guidance, therapentic or
research purposes. They may be confined to one individual or extended to several people. The following
discussions describe several types of interview.

Structured Interview :

Structured interview involves fight control over the format of questions and answers. It is like a
questionnaire which is administered face to face with a respondent. The researcher has a predetermined
list of questions. Each respondent is faced with identical questions. The choice of alternative answers is
restricted to a predetermined list. This type of interview is rigidly standardised and formal.

Structured interviews are often associated with social surveys where researchers are trying to collect
large volumes of data from a wide range of respondents.

Semi-Structured Interview :

In semi-structures interview, the interviewer also has a clear list of issues to be addressed and
questions to be answered. There is some flexibility in the order of the topics. In this type of interviewee is
given chance to develop his ideas and speak more widely on the issues raised by the researcher. The
answers are open-ended and more emphasis is on the interviewee elaborating points of interest.

Unstructured Interview :

In case of unstructured interview, emphasis is placed on the interviewee’s thoughts. The role of the
researcher is to be as unintruisve as possible. The researcher introduces a theme or topic and then letting
the interviewee develop his or her ideas and pursue his or her train of thought. Allowing interviewees to
speak their minds is a better way of discovering things about complex issues. It gives opportunity for in
depth investigations.

Single Interview :

This is a common form of semi structured or un-structured interview. It involves a meeting

between one researcher and one informant. It is easy to arrange this type of interview. It helps the
researcher to locate specific ideas wit specific people. It is also easy to control the situation in the part of
the interviewer.
Group Interview :

In case of group interview, more than one informant is involved. The numbers involved normally
about four to six people. Here you may think that it is difficult to get people together to discuss matters on
one occasion and how many voices can contribute to the discussion during any one interview. But the
crucial thing to bear in mind. Here is that a group interview is not an opportunity for the researcher to
questions to a sequence of individuals, taking turns around a table. ‘group’ is crucial here, because it tells
us that those present in the interview will interact with one another and that the discussion will operate at
the level of the group. They can present a wide range of information and varied view points.

According to Lewis –

“Group interviews have several advantages over individual interviews. In particular, they help to
reveal consensus views, may generate richer responses by allowing participants to challenge one another’s
views, may be used to verify research ideas of data gained through other methods and may enhance he
reliability of responses.”

The disadvantages of this type of interview is that the views of ‘quieter’ people does not come out.
Certain members may dominate the talk. The most disadvantage is that whatever opinions are expressed
are acceptable by the group irrespective of their opinions contrary to it. Private opinion does not given
importance.

Focus Group Interview :

This is an extremely popular form of interview technique. It consists of a small group of people,
usually between six and nine in number. This is useful for non-sensitive and non-sensitive and non-
controversial topics. The session usually revolve around a prompt, a trigger, some stimulus introduced by
the interviewer in order to ‘focus’ the discussion. The respondents are permitted to express themselves
completely, but the interviewer directs the live of thought. In this case, importance is given on collective
views rather than the aggregate view. It concentrates on particular event or experience rather than on a
general line of equality.

Requirements of a Good Interview :

As a tool of research good interview requires:
• Proper preparation.
• Skillful execution and
• Adequate recording and interpretation.
Preparation for Interview :
The follow actors need to be determined in advance of the actual interview:
• Purpose and information needed should be clear.
• Which type of interview best suited for the purpose should be decided.
• A clear outline and framework should be systematically prepared.
• Planning should be done for recording responses.

Execution of the Interview :

• Rapport should be established.
• Described information should be collected with a stimulating and encouraging discussion.
• Recording device should leased without distracting the interviewee.

Recording and Interpreting Responses :

• It is best to record through tape recorder.

• It the responses is to be noted down, it should be either noted simultaneously or immediately after it.
• Instead of recording responses, sometimes the researcher noted the evaluation directly interpreting the
responses.

Advantages of Interview :

Interviews techniques has the following advantages:

Depth Information :

Interviews are particularly good at producing data which deal with topics in depth and in detail.
Subjects can be probed, issues pursued lines of investigation followed over a relatively lengthy period.

Insights :

The researcher is likely to gain valuable insights based on the depth of the information gathered and
the wisdom of “key informants”.

Equipment :

Interviews require only simple equipment and build on conversation skills which researchers
already have.
Information Priorities :

Interviews are a good method for producing data based on informant’s priorities, opinions and
ideas. Informants have the opportunity to expand their ideas, explain their views and identify what regard
as their crucial factors.

Flexibility :

Interviews are more flexible as a method of data collection. During adjustments to the line of
enquiry can be made.

Validity :

Direct contact at the point of the interview means that data can be checked for accuracy and
relevance as they are collected.

High response rate :

Interviews are generally pre-arranged and scheduled for a convenient time and location. This
ensures a relatively high response rate.

Therapeutic:

Interviews can be a rewarding experience for the informant, compared with questionnaires,
observation and experiments, there is a more personal element to the method and people end to enjoy the
rather rare chance to talk about their ideas at length to a person whose purpose is to listen ad note the ideas
without being critical.

Disadvantages of Interviews :

Irrespective of the above advantages, it has the following disadvantages.

Time Consuming :

Analysis of data can be difficult and time consuming. Data preparation and analysis is “end
loaded” compared with, for instance, questionnaires, which are preceded and where data are ready for
analysis once they have collected. The transcribing and coding of interview data is a major task for the
researcher which occurs after the data have been collected.

Difficulty in data analysis :

This method produce non-standard responses. Semi-structured and unstructured interviews produce
data that are not pre coded and have a relatively open format.

Less Reliability :

Consistency and objectivity are hard to achieve. The data collected are, to an extent, unique owing
to the specific content and the specific individuals involved. This has an adverse effect on reliability.

Interviewer Effect :

The identify of the researcher may affect the statements of the interviewee. They may say what
they do or what they prefer to do. The two may not tally.

Inhibitions :

The tape recorder or video recorder may inhibit the important. The interview is an artificial
situation where people are speaking for the record and on the record and this can be daunting for certain
kinds of people.

Invasion of Privacy :

Interviewing can be an invasion of Privacy and may be upsetting for the informant.

Resources :
 The cost of interviewer’s fine, of travel and of transcription can be relatively high it the informants
are geographically widespread.

On the basis of the merits and limitations of the interview techniques it is used in many ways for
research and non-research purposes. This technique was used in common wealth teacher training study to
know the traits must essentials for success in teaching. Apart from being an independent data collection
tool, it may play an important role in the preparation of questionnaires and check lists which are to be put
to extensive use.

Check Your Progress - VII

Q.1 Explain different types of interview for the purpose of research.

Q.2 Write short notes on:

(a) Importance of Interview.

(b) Requisites of a good interview.

9.12 LET US SUM UP :

You would recall that we have touched upon the following learning items in this unit.
 For the purpose of collecting new relevant data foe a research study, the investigator needs to select
proper instruments termed as tools and techniques.

The major tools of research can be classified into broad categories of inquiry form, observation,
interview, social measures and Psychological tests.

Among the inquiry forms, we have discussed in this unit are Rating scale, attitude scale,
opinionnaire, questionnaire checklist and semantic differential scale. Observation and Interview are
explained as the techniques of data collection. In psychological tests, Aptitude tests and inventories are
discussed.

Rating scale is a technique which is designed or constructed to asses the personality of an

individual. It is very popular in testing applied psychology, vocational guidance and counseling as well as
in basic research. They measure the degree or amount of the indicated judgments.

Attitude scale is the device by which the feelings or beliefs of persons are described and measured
indirectly through securing their responses to a set of favourable statements. Thurstone and Likert scale
are commonly adopted for attitude scaling.

Opinionnaire is a special form of inquiry. It is used by the researcher to collect the opinions of a
sample of population. It is usually used in descriptive type research.

Questionnaire is a tool which used frequently. The purpose is to gathered information from widely
scattered sources. Data collected in written form through this tool.

Checklist is a selected list of words, Phrases, Sentences and paragraphs following which an
observer records a check mark to denote a presence or absence of whatever is being observed. It calls for a
simple yes / no judgments. The main purpose is to call attention to various aspects of an object or
situation, to see that nothing of importance is overlooked.

Semantic Differential Scale is a seven point scale and the end points of the scale are associated with
bipolar labels. This scale helps o determine overall similarities and differences among objects.

Aptitude tests are psychological tests attempt to product the capacities or the degree of achievement
expected from individuals in a particular activity. The purpose is to test a candidate’s profile.
 Inventory is a list, or record containing traits, preferences, attitudes interests or abilities used to
evaluate personal characteristics or skills. Strong’s vocational interest inventory is an example of interest
inventory.

Observation method is a technical in which the behaviour research subjects is watched and recorded
without any direct contact. It deals with the overt behaviour of persons in controlled or uncontrolled
situations.

Interview is an oral type of questionnaire where the subject supplies the needed information in a
face to face situation. It is specially appropriate for dealing with young children, illiterates, dull and the
abnormal.

Unit End Exercises:

1. State the characteristics of a questionnaire.

2. What are the disadvantages of an Interview?
3. Prepare items using Rating scale, Interview and Questionnaire for a research proposal.

Reference Books :

• Siddhu Kulbir Singh (1992). Methodology of Research in Education, Sterling Publisher, New Delhi.
• Sukhia S. P. and Mehrotra P. V. (1983). “Elements of educational Research” Allied Publisher Private
Limited New Delhi

• Denscombe, Martyn (1999). “The Good Research Guide” Viva Books Private Limited, New Delhi.
 10
DATA ANALYSIS AND REPORT WRITING
Unit Structure :
10.0 Objectives
10.1 Introduction
10.2 Types of Measurement Scale
10.3 Quantitative Data Analysis
10.3.1 Parametric Techniques
10.3.2 Non- Parametric Techniques
10.3.3 Conditions to be satisfied for using parametric techniques
10.3.4 Descriptive data analysis (Measures of central tendency, variability, fiduciary limits and
graphical presentation of data)
10.3.5 Inferential data analysis
10.3.6 Use of Excel in Data Analysis
10.3.7 Concepts, use and interpretation of following statistical techniques: Correlation, t-test, z-test,
ANOVA, Critical ratio for comparison of percentages and chi-square (Equal Probability and
Normal Probability Hypothesis).
10.4 Testing of Hypothesis

10.0 OBJECTIVES :

After reading this unit the student will be able to :

• Explain different types of measurement scales with appropriate examples.
• State the Conditions to be satisfied for using parametric techniques
• List the examples of parametric and non-parametric techniques.
• State the statistical measures of descriptive and inferential data analysis.
• Explain concepts of different statistical techniques of data analysis and their interpretation.
10.1 INTRODUCTION :

Statistical data analysis depends on several factors such as the type of measurement scale used, the
sample size, sampling technique used and the shape of the distribution of the data. These will be described
in this unit.

10.2 SCALES OF MEASUREMENT :

The level of measurement refers to the relationship among the values that are assigned to the
attributes for a variable. It is important to understand the level of measurement as it helps you to decide
how to interpret the data from the variable concerned. Second, knowing the level of measurement helps
you to decide which statistical techniques of data analysis are appropriate for the numerical values that
were assigned to the variables.
Types of Scales of Measurement

There are typically four scales or levels of measurement that are defined :

a. Nominal
b. Ordinal
c. Interval
d. Ratio

a. Nominal Scale : It is the lowest level of measurement. A nominal scale is simply some placing of data
into categories, without any order or structure. A simple example of a nominal scale is the terms we
use. For example, religion as the names of religion are categories where no ordering is implied.. Other
examples are gender, medium of instruction, school types and so on. In research activities, a YES/NO
scale is also an example of nominal scale. In nominal measurement the numerical values just "name"
the attribute uniquely. The statistical techniques of data analysis which can be used with nominal scales
are usually non-parametric.

b. Ordinal Scale : An ordinal scale is next up the list in terms of power of measurement. In ordinal
measurement, the attributes can be rank-ordered. Here, distances between attributes do not have any
meaning. For example, on a survey you might code Educational Attainment as 0=less than High
School; 1=some High School; 2=High School; 3=Junior College; 4=College degree; 5=post-graduate
degree. In this measure, higher numbers mean more education. But is distance from 0 to 1 same as 3 to
4? Of course not. The simplest ordinal scale is a ranking. There is no objective distance between any
two points on your subjective scale. An ordinal scale only lets you interpret gross order and not the
relative positional distances. The statistical techniques of data analysis which can be used with nominal
scales are usually non-parametric statistics. These would include Karl-Pearson’s coefficient of
correlation and non-parametric analysis of variance.

c. Interval Scale : In interval measurement, the distance between attributes does have meaning. For
example, when we measure temperature (in Fahrenheit), the distance between 30 and 40 is same as
distance between 70 and 80. The interval between values is interpretable. Because of this, it makes
sense to compute an average of an interval variable, whereas it does not make sense to do so for ordinal
scales. The rating scale is an interval scale. i.e. when you are asked to rate your job satisfaction on a 5
point scale, from strongly dissatisfied to strongly satisfied, you are using an interval scale. This means
that we can interpret differences in the distance along the scale. There is no absolute zero in the interval
scale. For example, if a student gets a score of zero on an achievement test, it does not imply that his
knowledge/ability in the subject concerned is zero as on another, similar test in the same subject
consisting of another set of questions, the student could have got a higher score. Thus a score of zero
does not imply a complete lack of the trait being measured in the subject. When variables are measured
in the interval scale, parametric statistical techniques of data analysis can be used. However, non-
parametric techniques can also be used with interval and ratio data.

d. Ratio Scale : Finally, in ratio scale, there is always an absolute zero that is meaningful. This means
that you can construct a meaningful fraction (or ratio) with a ratio variable. Weight is a ratio variable.
In educational research, most "count" variables are ratio, for example, the number of students in a
classroom. This is because you can have zero students and because it is meaningful to say that "...we
had twice as many students in a classroom as compared to another classroom." A ratio scale is the top
level of measurement. When variables are measured in the ratio scale, parametric statistical techniques
of data analysis can be used.

It is important to recognise that there is a hierarchy implied in the level of measurement idea. In
general, it is desirable to have a higher level of measurement (e.g., interval or ratio) rather than a lower one
(nominal or ordinal).
Check Your Progress - I
Q.1 State the different types of measurement scale.

Q.2 Give three examples where you can use the following scales of measurement :
(a) Nominal Scale
(b) Ordinal Scale
(c) Interval Scale
(d) Ratio Scale

10.3 QUANTITATIVE DATA ANALYSIS

10.3.1 Parametric and

10.3.2 Non-Parametric Techniques :

10.3.3 Conditions to be satisfied for Using Parametric Techniques :

These are as follows :

1. The sample size is greater than 30.
2. Data are normally distributed.
3. Data are measured in interval or ratio scales.
4. Variances of different sub-groups are equal or nearly equal.
5. The sample is selected randomly.
6. Observations are independent.

10.3.4 Descriptive Data Analysis

Descriptive statistics are used to present quantitative descriptions in a manageable form. In a

research study, we may have lots of measures. Or we may measure a large number of people on one
measure. Descriptive statistics help us to simply large amounts of data in a sensible way. Each descriptive
statistic reduces lots of data into a simpler summary. For instance, consider a simple number used to
summarize how well a batter is performing in baseball, the batting average. This single number is simply
the number of hits divided by the number of times at bat (reported to three significant digits). A batter who
is hitting .333 is getting a hit one time in every three at bats. One batting .250 is hitting one time in four.
The single number describes a large number of discrete events. For example, we may describe the
performance of students of a class in terms of their average performance. Descriptive statistics provide a
powerful summary that may enable comparisons across people or other units.
Measures of Central Tendency : These include Mean, Median and Mode which indicate the average
value of the variable being studied (Mean), the value above and below which lie 50% of the sample values
(Median) and the value which occurs the maximum number of times in the sample (Mode). These help in
determining the extent of normality of the distribution of scores on the variable being studied.

Measures of Variability : These include the standard deviation, skewness and kurtosis. The standard
deviation indicates the deviation of each score from the Mean. Skewness indicates whether majority of the
scores lie to the left of the Mean (positively skewed), to the right of the Mean (negatively skewed) or bell-
shaped (normally distributed). Kurtosis indicates whether the distribution of the scores is flat (platykurtic),
peaked (leptokurtic) or bell-shaped (mesokurtic).

Fiduciary Limits : These indicates the interval (or the fiduciary limits) within which the Mean of the
population will lie at 0.95 or 0.99 levels of confidence. The fiduciary limits or the confidence interval of
the population Mean is estimated based on the sample mean. The sample Mean is known as the ‘Statistic’
and the population mean is known as the “parameter’. The computation of population Mean requires the
use of Standard Error of the Mean. Similarly, fiduciary limits or the confidence interval of the population
standard deviation is also computed.

Graphical Presentation of Data : This includes bar diagrams, pie charts and line graph. The line graph is
usually used to represent the distribution of the scores obtained on a variable with the objective of
indicating the shape of the distribution. The bar diagram are used for making comparisons of Mean scores
on the variable being studied in various sub-groups such as boys v/s girls, urban v/s rural, private-aided v/s
private-unaided v/s municipal schools, SSC v/s CBSE v/s ICSE v/s IGCSE schools and so on. Pie charts
are used to indicate proportion of different sub-groups in the sample or the variance of a specific variable
associated with another variable.

Check Your Progress - I

Q.1 Explain the meaning of parametric and non-[parametric techniques of data analysis.

Q.2 State the conditions necessary for using parametric techniques of data analysis.

Q.3 Which are the measures of central tendency and variability? Why is it necessary to compute these?
Q. 4 You want to (i) compare the Mean Academic Achievement of boys and girls, (ii) show whether the
Academic Achievement scores of students are normally distributed or not and (iii) show the
proportion of boys and girls in the total sample. State the graphical techniques to be used in each
of these cases.

10.3.5 Inferential Data Analysis

Descriptive data analysis only describes the data and the characteristics of the sample in terms of
statistics. Its findings could not be generalised to larger population.

On the other hand, the findings of the inferential analysis can be generalised to larger population.

10.3.6 Use of Excel in Data Analysis : The MS-Excel is an excellent tool for analysing data using
statistical techniques descriptive statistics such as the Mean, Medial, Mode, SD, Skewness and Kurtosis
and inferential techniques including t-test, ANOVA, correlation. It also helps in presenting data
graphically through bar diagrams, line graph and pie chart.

10.3.7 Concepts, Use and Interpretation of Statistical Techniques

A. Correlation : When the variables are in the interval or ratio scale, correlation and regression
coefficients are computed. A Pearson product-moment correlation coefficient is a measure of linear
association between two variables in interval or ratio scale. The measure, usually symbolised by the
letter r, varies from –1 to +1, with 0 indicating no linear association. The word “correlation” is
sometimes used in a non-specific way as a synonym for “association.” Here, however, the Pearson’s
product-moment correlation coefficient is a measure of linear association computed for a specific set
of data on two variables. For example, if a researcher wants to ascertain whether teachers’ job
satisfaction is related to their school climate, Pearson’s product-moment correlation coefficient could
be computed for teachers’ scores on these two variables.
Interpretation of “r” : This takes into account four major aspects as follows:

a. Level of significance (usually at 0.01 or 0.05 levels in educational research).

b. Magnitude of “r”: In general, the following forms the basis of interpreting the magnitude of the
“r”:

No. Value of “r” Magnitude

1 0.00-0.20 Negligible
2 0.21-0.40 Low
3 0.41-0.60 Moderate
 4 0.61-0.80 Substantial
5 0.81-1.00 Very High

c. Direction of “r”: The “r” could be positive, negative or zero. (i) A positive “r” signifies that the
relationship between two variables is direct i.e. if the value of one variable is high, the other is also
expected to be high. For example, if there is a substantial relationship between IQ and Academic
Achievement of students, it implies that higher the IQ of students. higher is likely to be their
Academic Achievement. (ii) A negative “r” signifies that the relationship between two variables is
inverse i.e. if the value of one variable is high, the other is also expected to be low. For example, if
there is a substantial relationship between Anxiety and Academic Achievement of students, it
implies that higher the Anxiety of students. lower is likely to be their Academic Achievement. (iii)
The relationship between two variables could be zero.

d. The Coefficient of Determination : It refers to the percentage of variability in one variable that is
associated with variability in the other variable. It is computed using the formula 100r2. The square
of the correlation coefficient i.e. 100r2 is another PRE (proportionate reduction in error) measure of
association.

B. t-test : A t-test is used to compare the Mean Scores obtained by two groups on a single variable. It is
also used when F-ratio in ANOVA is found to be significant and the researcher wants to compare the
Mean scores of different groups included in the ANOVA. It can also be used to compare the Mean
Academic Achievement of two groups such as (i) boys and girls or (ii) Experimental and Control
groups etc. The t-test was introduced in 1908 by William Sealy Gosset, a chemist working in Ireland.
His pen name was "Student".
The assumptions on which the t-test is used are as follows:
(a) Data are normally distributed. This can be ascertained by using normality tests such as the Shapiro-
Wilk and Kolmogorov-Smirnov tests.
(b) Equality of variances which can be tested by using the F-test or the more robust Levene’s test,
Bartlett’s test or the Brown-Forsythe test.
(c) Samples may be independent or dependent, depending on the hypothesis and the type of samples. For
the inexperienced researcher, the most difficult issue is often whether the samples are independent or
dependent. Independent samples are usually two randomly selected groups unrelated to teach other
such as boys and girls or private-aided and private-unaided schools in a causal-comparative research.
On the other hand, dependent samples are either two groups matched (or a "paired" sample) on some
variable (for example, IQ or SES) or are the same people being tested twice (called repeated
measures as is done in an experimental design).

Dependent t-tests can also used for matched-paired samples, where two groups are matched on a
particular variable. For example, if we examined the IQ of twins, the two groups are matched on genetics.
This would call for a dependent t-test because it is a paired sample (one child/twin paired with one another
child/twin). However, when we compare 100 boys and 100 girls, with no relationship between any
particular boy and any particular girl, we would use an independent samples test. Another example of a
matched sample would be to take two groups of students, match each student in one group with a student
in the other group based on IQ and then compare their performance on an achievement test. Alternatively,
we assign students with low scores and students with high scores in two groups and assess their
performance on an achievement test independently. An example of a repeated measures t-test would be if
one group were pre-tested and post-tested as is done in educational research quite often especially in
experiments. If a teacher wanted to examine the effect of a new set of textbooks on student achievement,
he could test the class at the beginning of the treatment (pre-test) and at the end of the treatment (post-test).
A dependent t-test would be used, treating the pre-test and post-test as matched variables (matched by
student).
Types of t-test :
(a) Independent one-sample t-test : Suppose in a research, on the basis of past research, the researcher
finds that the Mean Academic Achievement of students in Mathematics is 50 with a SD of 12. If the
researcher wants to know whether this year’s students’ Academic Achievement in Mathematics is
typical, he takes μo = 50 which is the population Mean and S = 12 where S is the population SD.
Suppose N = 36. In testing the null hypothesis that the population mean is equal to a specified value μ0,
one uses the statistic t the formula for which is follows:
t = [M - μo ] ÷ √S/N
where S is the population standard deviation and N is the sample size. The degrees of freedom used in
this test is N − 1.
(b) Independent two-sample t-test : This is of the following three types:
(i) Equal sample sizes, equal variance : This test is only used when both the samples are of the same size
i.e. N1 = N2 = N and when it can be assumed that the two distributions have the same variance. Its
formula is as follows:
Standard Error of the Difference between Means (SED)
= √ (σ21 + σ22) ÷ N )
t = (M1 – M2) ÷ SED
Where,
M1= Mean of Group 1
M2= Mean of Group 2
σ1= SD of Group 1
σ2= SD of Group 2
(ii) Unequal sample sizes, equal variance : This test is used only when it can be assumed that the two
distributions have the same variance. The t statistic to test whether the means are different can be
calculated as follows:

Standard Error of the Difference between Means (SED)

= √ (σ21 / N1 + σ22/N2)
t = (M1 – M2) ÷ SED
Where,
M1= Mean of Group 1
M2= Mean of Group 2
σ1= SD of Group 1
σ2= SD of Group 2
(iii) Unequal sample sizes, unequal variance : This test is used only when the two sample sizes are unequal
and the variance is assumed to be different. The t statistic to test whether the means are different can
be calculated as follows:
Standard Error of the Difference between Means (SED)
= √ (σ21 / N1 + σ22/N2)
t = (M1 – M2) ÷ SED
However, the tabulated t (tt) against which the obtained t (to) is compared in order test its
significance is calculated differently using the following formula :
Suppose for Sample 1, for df = N-1, tabulated t (tt) at 0.05 level of significance = x
and
Sample 2, for df = N-1, tabulated t (tt) at 0.05 level of significance = y.
SE1 = Standard Error of M1
SE2 = Standard Error of M2
Corrected tabulated t (tt) at 0.05 level of significance
= (SE21 × x) + (SE22 × y) ÷ (SE21 + SE22)
Where,
M1= Mean of Group 1
M2= Mean of Group 2
σ1= SD of Group 1
σ2= SD of Group 2
(c) Dependent t-test for paired samples : This test is used when the samples are dependent; that is, when
there is only one sample that has been tested twice (repeated measures) or when there are two samples
that have been matched or "paired" as is usually done in experimental research. Its formula is as
follows:
Standard Error of the (Mean)1 = σ1 ÷ √ N1 = SEM1
Standard Error of the (Mean)1 = σ2 ÷ √ N2 = SEM2
Standard Error of the Difference between Means (SED)
= √ (SEM1+ SEM2 – 2r. SEM1 SEM2)
t = (M1 – M2) ÷ SED
Where,
M1= Mean of Pre-test Scores
M2= Mean of Post-test Scores
σ1= SD of Group 1
σ2= SD of Group 2
 r = Coefficient of Correlation between Pre-test and Post-test Scores
Alternatives to the t test
The t test can be used to test the equality of the means of two normal populations with unknown,
but equal, variance. To relax the normality assumption, a non-parametric alternative to the t test can be
used and the usual choices are (a) for independent samples, the Mann-Whitney U test and (b) for related
samples, either the binomial test or the Wilcoxin signed-rank test. To test the equality of the means of
more than two normal populations, an analysis of variance can be performed.
z-test : It is used to compare two coefficients of correlation. For example, a researcher studies the
relationship between job satisfaction and school climate among two groups, viz., male and female teachers.
Further, he may want to ascertain whether this relationship differs among male and female teachers. In this
case, he will have two coefficients of correlation, r1 for male teachers and r2 for male teachers for the
variables of job satisfaction and school climate. In such a case, z-test is used the formula for which is as
follows:

z = (z1 – z2) ÷ √(1 / N1-3 + 1/ N2-3)

ANOVA : Analysis of variance (ANOVA) is used for comparing more than two groups on a single
variable. It a collection of statistical models and their associated procedures, in which the observed
variance is partitioned into components due to different explanatory variables. In its simplest form
ANOVA gives a statistical test of whether the means of several groups are all equal, and therefore
generalizes Student’s two-sample t-test to more than two groups.

There are three conceptual classes of such models:

1. Fixed-effects model assumes that the data came from normal populations which may differ only in
their means. The fixed-effects model of analysis of variance applies to situations in which the
experimenter applies several treatments to the subjects of the experiment to see if the response
variable’s values change. This allows the experimenter to estimate the ranges of response variable
values that the treatment would generate in the population as a whole.

2. Random-effects model assumes that the data describe a hierarchy of different populations whose
differences are constrained by the hierarchy. Random effects models are used when the treatments
are not fixed. This occurs when the various treatments (also known as factor levels) are sampled
from a larger population. Because the treatments themselves are random variables, some
assumptions and the method of contrasting the treatments differ from ANOVA.

3. Mixed-effect model describes situations where both fixed and random effects are present.

Types of ANOVA : These are as follows :

(a) One-way ANOVA : It is used to test for differences among two or more independent groups.
Typically, however, the one-way ANOVA is used to test for differences among three or more
groups, since the two-group case can be covered by student’s t-test. When there are only two means
to compare, the t-test and the F-test are equivalent with F = t2. For example, a researcher wants to
compare students’ attitude towards the school on the basis of school types (SSC, CBSE and ICSE).
In this case, there is one dependent variable, namely, attitude towards the school and three groups,
namely, SSC, CBSE and ICSE schools. Here, the one-way ANOVA is used to test for differences
in students’ attitude towards the school among the three groups.

(b) One-way ANOVA for repeated measures : It is used when the subjects are subjected to repeated
measures. This means that the same subjects are used for each treatment. Note that this method can
 be subject to carryover effects. This technique is often used in experimental research in which we
want to compare three or more groups on one dependent variable which is measured twice i.e. as
pre-test and post-test.

(c) Two-way ANOVA : It is used when the researcher wants to study the effects of two or more
independent or treatment variables. it is also known as factorial ANOVA. The most commonly used
type of factorial ANOVA is the 2×2 (read as "two by two", as you would a matrix) design, where
there are two independent variables and each variable has two levels or distinct values. Two-way
ANOVA can also be multi-level such as 3×3, etc. or higher order such as 2×2×2, etc. but analyses
with higher numbers of factors are rarely done by hand because the calculations are lengthy.
However, since the introduction of data analytic software, the utilization of higher order designs
and analyses has become quite common. For example, a researcher wants to compare students’
attitude towards the school on the basis of (i) school types (SSC, CBSE and ICSE) and (ii) gender.
In this case, there is one dependent variable, namely, attitude towards the school and two
independent variables, viz., (i) school types including three levels, namely, SSC, CBSE and ICSE
schools and (ii) gender including two levels, namely, boys and girls. Here, the two-way ANOVA is
used to test for differences in students’ attitude towards the school on the basis of (i) school types
and (ii) gender. This is an example of 3×2 two-way ANOVA as there are three levels of school
types, namely, SSC, CBSE and ICSE schools and two levels of gender, namely, boys and girls. it is
known as two-way ANOVA as it involves comparing one dependent variable (attitude towards the
school) on the basis of two independent variables, viz., (i) school types and (ii) gender.

(d) MANOVA: When one wants to compare two or more independent groups in which the sample is
subjected to repeated measures such as pre-test and post-test in an experimental study, one may
perform a factorial mixed-design ANOVA i.e. Multivariate Analysis of Variance or MANOVA in
which one factor is a between-subjects variable and the other is within-subjects variable. This is a
type of mixed-effect model. It is used when there is more than one dependent variable.

(e) ANCOVA : While comparing two groups on a dependent variable, if it is found that they differ on
some other variable such as their IQ, SES or pre-test, it is necessary to remove these initial
differences. This can be done through using the technique of ANCOVA.

Assumptions of Using ANOVA

1. Independence of cases.
2. Normality of the distributions in each of the groups.
3. Equality or homogeneity of variances, known as homoscedasticity i.e. the variance of data in groups
should be the same. Levene’s test for homogeneity of variances is typically used to confirm
homoscedasticity. The Kolmogorov-Smirnov or the Shpiaro-Wilk test may be used to confirm
normality. According to Lindman, F-test is unreliable if there are deviations from normality whereas
Ferguson and Takane claim that the F-test is robust. The Kruskal-Wallis test is a non-parametric
alternative which does not rely on an assumption of normality. These together form the common
assumption that the errors are independently, identically, and normally distributed for fixed effects
models.

Critical Ratio for Comparison of Percentages :  This technique is used when the researcher wants to
compare two percentages. Its formula is as follows :
(i) For uncorrelated percents :
CR = P1-P2 ÷ (SE of Percentage)
Where,
P1 = Percentage occurrence of observed behaviour in Group 1
P2 = Percentage occurrence of observed behaviour in Group 2
P = (N1P1 + N2P2) ÷ (N1+ N2)
P = Percent occurrence of observed behaviour
Q = 1=P
SE of difference between percentages = √ [PQ(1/ N1 + 1/ N2)]
(ii) For correlated percents :
CR = P1-P2 ÷ (SE of Percentage)
Where,
P1 = Percentage occurrence of observed behaviour in Group 1
P2 = Percentage occurrence of observed behaviour in Group 2
P = (N1P1 + N2P2) ÷ (N1+ N2)
P = Percent occurrence of observed behaviour
Q = 1=P
SE of difference between percentages
= √[(SE) P1+(SE) P2 - 2r(SE) P1 ×(SE) P2]

The obtained CR is compared with tabulated CR given in statistical table to test its significance.
Chi-square (Equal Probability and Normal Probability Hypothesis): A chi-square test (also chi-
squared or χ2 test) is any statistical test in which the test statistic has a chi-squared distribution when the
null hypothesis is true, or any distribution in which the probability distribution of the test statistic
(assuming the null hypothesis is true) can be made to approximate a chi-square distribution as closely as
desired by making the sample size large enough. Chi-square is a statistical test commonly used to compare
observed data with data we would expect to obtain according to a specific hypothesis. For example, if a
researcher expects parents’ attitude towards sex education to be provided in schools to be normally
distributed, then he might want to know about the "goodness to fit" between the observed and expected
results i.e. whether the deviations (differences between observed and expected) the result of chance, or
whether they are due to other factors. The chi-square test tests the null hypothesis, which states that there
is no significant difference between the expected and observed result. If it is assumed that the expected
frequencies are equally distributed in all the cells, the chi-square test is known as equal distribution
hypothesis. On the other hand, if it is assumed that the frequencies are expected to be distributed normally,
the chi-square test is known as normal distribution hypothesis. The chi-square (χ 2) test measures the
alignment between two sets of frequency measures. These must be categorical counts and not percentages
or ratios measures.

Thus, Chi-squared, χ2 = ∑(fo - fe)2 / fe

where,
fo = observed frequency and
fe = expected frequency.
 It may be noted that the expected values may need to be scaled to be comparable to the observed
values. A simple test is that the total frequency/count should be the same for observed and expected
values. In a table, the expected frequency, if not known, may be estimated as: fe = (row total) x (column
total) / N, where N is the total number of all the rows (or columns). The obtained Chi Square is compared
with that given in the Chi Square table to determine whether the comparison shows significance.

In a table, the degrees of freedom are computed as follows :

df = (R - 1) × (C - 1),
Where R = number of rows
C = number of columns. 
 
Chi-square indicates whether there is a significant association between variables, but it does not
indicate just how significant and important this is.

Check Your Progress – II

Suggest appropriate statistical technique of data analysis in the following cases :

(a) You want to find out the relationship between academic achievement and motivation of students.

(b) You want to compare the academic achievement of boys and girls :

(c) You are conducting a survey of teachers’ opinion about admission criteria for junior college
admissions and want to know whether their opinion is favourable or not :

(d) You want to compare the academic achievement of students from private-aided, private-unaided
and municipal schools.
 (e) You want to compare whether the percentage of girls and boys enrolling for secondary school :

10.4 TESTING OF HYPOTHESIS :

There are a number of ways in which the testing of the hypothesis may bear on a theory. According
to Wallace, it can
(i) Lend confirmation to the theory by not disconfirming it.
(ii) Modifying the theory by disconfirming it, but not at a crucial point; or
(iii) Overthrow the theory by disconfirming it at a crucial point in its logical structure, or in its
competitive value as compared with rival theories.
Methods of Testing of Hypothesis
There are three major methods of testing of hypothesis as follows:

1. Verification : The best test of a hypothesis is to verify whether the inferences reached from the
propositions are consistent with the observed facts. Verification is of two types as follows: (a) Direct
Verification by Observation or Experimentation and (b) Indirect Verification by deducing
consequences from the supposed cause and comparing them with the facts of experience. This
necessitates the application of the principle of deduction.

2. Experimentum Crucis : This is known as crucial instance or confirmatory test. When a researcher is
confronted with two equally competent but contradictory hypotheses, he needs one instance which
explains the phenomenon and helps in accepting any one of the hypotheses. When this is done through
an experiment, the experiment is known as ‘Experimentum Crucis’.

3. Consilience of Inductions : This refers to the power which a hypothesis has of ‘explaining and
determining cases of a kind different from those which were contemplated in the formation of
hypothesis’. In other words, the hypothesis is accepted and its value is greatly enhanced when it is
found to explain other facts also in addition to those facts which it was initially designed to explain.

Errors in Testing of Hypothesis:

A researcher tests the null hypothesis using some statistical technique. Based on the test of
statistical significance he / she accepts or rejects the null hypothesis and thereby either rejects or accepts
the research hypothesis respectively.
If the null hypothesis is true and is accepted or when it is false and is rejected, the decisions taken
are true.
However, error in testing of hypothesis occurs under the following two situations:
(i) If the null hypothesis (H0) is true but is rejected and
(ii) If the null hypothesis (H0) is false but is accepted.
The former is the example of Type I error while the latter is the example of Type II error in testing of
hypothesis.
 Type I error occurs when a true null hypothesis is rejected. It is also known as Alpha (α) error.
Type II error occurs when a false null hypothesis is accepted. It is also known as Beta (β) error.
This is shown in the following table :

Possible Outcomes
Accept H0 Reject H0
Possible H0 True Correct Decision Type I error
Situations (α error)
H0 False Type II error Correct Decision
(β error)

When the sample size N is fixed, if we try to reduce Type I error, the chances of making Type II error
increase. Both types of errors cannot be reduced simultaneously. More about this will be discussed in the
section on statistical analysis of data.
Check Your Progress – III
(a) What are the major methods of hypothesis testing ?

(b) What are the different types of errors in the hypothesis testing?

Suggested Readings

1. Guilford, J. P. and Fruchter, B. Fundamental Statistics in psychology and Education. Singapore :

McGraw –Hill Book Company. 1981.

2. Best, J. and Kahn, J. Research in Education (9 ed), New Delhi: Prentice Hall of India Pvt. Ltd. 2006.

3. Garret, H. E. Statistics in Psychology and Education. New York: Longmans Green and Co. 5th edition
1958.
 
 
 
 11
QUALITATIVE DATA ANALYSIS

Unit Structure:
11.0 Objectives
11.1 Introduction
11.2 Qualitative Data Analysis
• Data Reduction and Classification
• Analytical Induction
• Constant Comparison

11.0 OBJECTIVES :
After reading this unit the student will be able to :
• Explain the meaning of qualitative data analysis.
• State the broad focus of qualitative research.
• State the specific research questions usually formulated in qualitative research.
• State the principles and characteristics of qualitative data analysis.
• Explain the strategies of qualitative data analysis.

11.1 INTRODUCTION :

Meaning: Qualitative data analysis is the array of processes and procedures whereby a researcher provides
explanations, understanding and interpretations of the phenomenon under study on the basis of meaningful
and symbolic content of qualitative data. It provides ways of discerning, examining, comparing and
contrasting and interpreting meaningful patterns and themes. Meaningfulness is determined by the specific
goals and objectives of the topic at hand wherein the same set of data can be analysed and synthesised
from multiple angles depending on the research topic. It is based on the interpretative philosophy.
Qualitative data are subjective, soft, rich and in-depth descriptions usually presented in the form of words.
The most common forms of obtaining qualitative data include semi-structured and unstructured interviews,
observations, life histories and documents. The process of analysing is difficult rigorous.
Broad Focus of Qualitative Research : These include finding answers to the following questions:
• What is the interpretation of the world from the participants’ perspective?
• Why do they have a particular perspective?
• How did they develop such a perspective?
• What are their activities?
• How do they identify and classify themselves and others?
• How do they convey their perspective of their situation?
 • What patterns and common themes surface in participants’ responses dealing with specific items?
How do these patterns shed light on the broader study questions?
• Are there any deviations from these patterns? If so, are there any factors that might explain these
atypical responses?
• What stories emerge from these responses? How do these stories help in illuminating the broader
study questions?
• Do any of these patterns or findings suggest additional data that may be required? Do any of the
study questions need to be revised?
• Do the patterns that emerge substantiate the findings of any corresponding qualitative analysis that
have been conducted? If not, what might explain these discrepancies?
Specific Research Questions Usually Formulated in Qualitative
Research
• What time did school start in the morning?
• What would students probably have to do before going to school ?
• What was the weather like in the month of data collection?
• How did the students get from home to school ?
• What were the morning activities ?
• What did the students do in the recess?
• What were the activities after recess?
• What was the classroom environment like?
• What books and instructional materials were used?
• At what time did the school got over?
• What would students probably have to do after school got over ?
• What kind of homework was given and how much time it required?
Before describing the process of qualitative data analysis process, it is necessary to describe the
terms associated with process.
Principles of Qualitative Data Analysis
These are as follows;
1 Proceeding systematically and rigorously (minimise human error).
2 Recording process, memos, journals, etc.
3 Focusing on responding to research questions.
4 Identifying appropriate level of interpretation suitable to a situation.
5 Simultaneous process of inquiry and analysis.
6 Seeking to explain or enlighten.
7 Evolutionary/emerging.

Characteristics of Qualitative Data Analysis:

According to Seidel, the process has the following characteristics :
a. Iterative and Progressive: The process is iterative and progressive because it is a cycle that keeps
repeating. For example, if you are thinking about things, you also start noticing new things in the data.
You then collect and think about these new things. In principle the process is an infinite spiral.

b. Recursive : The process is recursive because one part can call you back to a previous part. For
example, while you are busy collecting things, you might simultaneously start noticing new things to
collect.

c. Holographic : The process is holographic in that each step in the process contains the entire process.
For example, when you first notice things, you are already mentally collecting and thinking about those
things.

11.2      COMPONENTS OF QUALITATIVE DATA ANALYSIS : 
   

According  to  Miles  and  Huberman,  following  are  the  major  components  of  qualitative  data 
analysis :  
 
(A) Data Reduction : "Data reduction refers to the process of selecting, focusing, simplifying, abstracting,
and transforming the data that appear in written up field notes or transcriptions." First, the mass of data has
to be organized and somehow meaningfully reduced or reconfigured. These data are condensed so as to
make them more manageable. They are also transformed so that they can be made intelligible in terms of
the issues being addressed. Data reduction often forces choices about which aspects of the accumulated
data should be emphasised, reduced or set aside completely for the purposes of the topic at hand. Data in
themselves do not reveal anything and hence it is not necessary to present a large amount of unassimilated
and uncategorized data for the reader's consumption in order to show that you are "perfectly objective". In
qualitative analysis, the researcher uses the principle of selectivity to determine which data are to be
singled out for description. This usually involves some combination of deductive and inductive analysis.
While initial categorizations are shaped by pre-established research questions, the qualitative researcher
should remain open to inducing new meanings from the data available. Data reduction should be guided
primarily by the need to address the salient question(s) in a research. This necessitates selective
winnowing/sifting which refers to removing data from a group so that only the best ones which are
relevant for answering particular research questions are left. This is difficult as not only qualitative data are
very rich but also because the person who analyses the data also often plays a direct, personal role in
collecting them. The process of data reduction starts with a focus on distilling what the different
respondents report about the activity, practice or phenomenon under study to share knowledge. The
information given by various categories of sample is now compared – such as the information given by
experienced and new teachers or the information given by teachers, principal, students and/or parents
about central themes of the research. In setting out these similarities and dissimilarities, it is important not
to so "flatten" or reduce the data that they sound like close-ended survey responses. The researcher should
ensure that the richness of the data is not unfairly and unnecessarily diluted. Apart from exploring the
specific content of the respondents' views, it is also a good idea to take note of the relative frequency with
which different issues are raised, as well as the intensity with which they are expressed.
(B) Data Display : Data display provides "an organized, compressed assembly of information that
permits conclusion drawing..." A display can be an extended piece of text or a diagram, chart or matrix
that provides a new way of arranging and thinking about the more textually embedded data. Data displays,
permits the researcher to extrapolate from the data enough to begin to identify systematic patterns and
interrelationships. At the display stage, additional, higher order categories or themes may emerge from the
data that go beyond those first discovered during the initial process of data reduction. Data display can be
extremely helpful in identifying whether a system is working effectively and how to change it. The
qualitative researcher needs to discern patterns of among various concepts so as to gain a clear
understanding of the topic at hand. Data could be displayed using a series of flow charts that map out any
critical paths, decision points, and supporting evidence that emerge from establishing the data for each site.
The researcher may (1) use the data from subsequent sites to modify the original flow chart of the first site,
(2) prepare an independent flow chart for each site; and/or (3) prepare a single flow chart for some events
(if most sites adopted a generic approach) and multiple flow charts for others.
(C) Conclusion Drawing and Verification : Conclusion drawing requires a researcher to begin to
decide what things mean. He does this by noting regularities, patterns (differences/similarities),
explanations, possible configurations, causal flows, and propositions. This process involves stepping back
to consider what the analysed data mean and to assess their implications for the questions at hand.
Verification, integrally linked to conclusion drawing, entails revisiting the data as many times as necessary
to cross-check or verify these emergent conclusions. Miles and Huberman assert that "The meanings
emerging from the data have to be tested for their plausibility, their sturdiness, their ‘confirmability’ - that
is, their validity". Validity in this context refers to whether the conclusions being drawn from the data are
credible, defensible, warranted, and able to withstand alternative explanations. When qualitative data are
used with the intension of identifying dimensions/aspects of a concept for designing/developing a
quantitative tool, this step may be postponed. Reducing the data and looking for relationships will provide
adequate information for developing other instruments.

Miles and Huberman describe several tactics of systematically examining and re-examining the data
including noting patterns and themes, clustering cases, making contrasts and comparisons, partitioning
variables and subsuming particulars in the general which can be employed simultaneously and iteratively
for drawing conclusions in a qualitative research. This process is facilitated if the theoretical or logical
assumptions underlying the research are stated clearly. They further identify 13 tactics for testing or
confirming findings, all of which address the need to build systematic "safeguards against self-delusion"
into the process of analysis.

THE PROCEDURES OF QUALITATIVE DATA ANALYSIS

These are as follows:
1 Coding/indexing
2 Categorisation
3 Abstraction
4 Comparison
5 Dimensionalisation
6 Integration
7 Iteration
8 Refutation (subjecting inferences to scrutiny)
9 Interpretation (grasp of meaning - difficult to describe procedurally)

Steps of Qualitative Data Analysis

The Logico-Inductive process of data analysis is as follows;
• Analysis is logico-inductive.
• Data are mostly verbal.
• Observations are made of behaviours, situations, interactions, objects and environment.
• Becoming familiar with the data.
 • Data are examined in depth to provide detailed descriptions of the setting, participants and activity
(describing).
• Coding pieces of data.
• Grouping them into potential themes (classifying) which are identified from observations through
(reading / memoing).
• Themes are clustered into categories.
• Categories are scrutinised to discover patterns.
• Explanations are made from patterns.
• Interpreting and synthesizing the organised data into general written conclusions or understandings
based on what is observed and are stated verbally (interpreting).
• These conclusions are used to answer research questions.
Terms associated with Qualitative Data Analysis:
• Data : It is the information obtained in the form of words.
• Category : It is a classification of ideas and concepts. When concepts in the data are examined and
compared with one another and connections are made, categories are formed. Categories are used to
organise similar concepts into distinct groups.
• Pattern : It is a link or the relationship between two or more categories that further organises the
data and that usually becomes the primary basis of organising and reporting the outcomes of the
study. Pattern seeking means examining the data in as many ways as possible through
understanding the complex links between situations, processes, beliefs and actions.
Qualitative data analysis is a predominantly an inductive process of organizing data into categories
and patterns (relationship) among the categories.
Types of Codes Usually Used in Educational Research :
Seidel identifies three major types of codes in qualitative analysis of data:
1. Descriptive Coding : This is when coding is used to describe what is in the data.

2. Objectivist Coding : According to Seidel and Kelle, an objectivist approach treats code words as
“condensed representation of the facts described in the data”. Given this assumption, code words
can be treated as substitutes for the text and the analysis can focus on the codes instead of the text
itself. You can then imitate traditional distributional analysis and hypothesis testing for qualitative
data. But first you must be able to trust your code words. To trust a code word you need: 1) to
guarantee that every time you use a code word to identify a segment of text that segment is an
unambiguous instance of what that code word represents, 2) to guarantee that you applied that code
word to the text consistently in the traditional sense of the concept of reliability, and 3) to guarantee
that you have identified every instance of what the code represents. If the above conditions are met,
then: 1) the codes are adequate surrogates for the text they identify, 2) the text is reducible to the
codes, and 3) it is appropriate to analyze relationships among codes. If you fall short of meeting
these conditions then an analysis of relationships among code words is risky business.

3. Heuristic Coding : In a heuristic approach, code words are primarily flags or signposts that point to
things in the data. The role of code words is to help you collect the things you have noticed so you
can subject them to further analysis. Heuristic codes help you reorganize the data and give you
different views of the data. They facilitate the discovery of things, and they help you open up the
data to further intensive analysis and inspection. The burdens placed on heuristic codes are much
less than those placed on objective codes. In a heuristic approach code words more or less represent
the things you have noticed. You have no assurance that the things you have coded are always the
 same type of thing, nor that you have captured every possible instance of that thing in your coding
of the data. This does not absolve you of the responsibility to refine and develop your coding
scheme and your analysis of the data. Nor does it excuse you from looking for “counter examples”
and “confirming examples” in the data. The heuristic approach does say that coding the data is
never enough. It is the beginning of a process that requires you to work deeper and deeper into your
data. Further, heuristic code words change and evolve as the analysis develops. The way you use
the same code word changes over time. Text coded at time one is not necessarily equivalent with
text coded at time two. Finally, heuristic code words change and transform the researcher who, in
turn, changes and transforms the code words as the analysis proceeds.

Bogdan and Biklen (1998) provide common types of coding categories, but emphasize that your
hypotheses shape your coding scheme.
Setting/Context codes provide background information on the setting, topic, or subjects.
1. Defining the Situation codes categorize the world view of respondents and how they see themselves
in relation to a setting or your topic.
2. Respondent Perspective codes capture how respondents define a particular aspect of a setting. These
perspectives may be summed up in phrases they use, such as, "Say what you mean, but don't say it
mean."
3. Respondents' Ways of Thinking about People and Objects codes capture how they categorize and
view each other, outsiders, and objects. For example, a dean at a private school may categorize
students: "There are crackerjack kids and there are junk kids."
4. Process codes categorize sequences of events and changes over times.
5. Activity codes identify recurring informal and formal types of behaviour.
6. Event codes, in contrast, are directed at infrequent or unique happenings in the setting or lives of
respondents.
7. Strategy codes relate to ways people accomplish things, such as how instructors maintain students'
attention during lectures.
8. Relationship and social structure codes tell you about alliances, friendships, and adversaries as well
as about more formally defined relations such as social roles.
9. Method codes identify your research approaches, procedures, dilemmas, and breakthroughs.

Check Your Progress - I

(a) State the components of qualitative data analysis.

(b) Which are the different types of codes used in qualitative research in education?

(c) What are the terms associated with qualitative data analysis?
 (d) Explain the steps of qualitative data analysis.

STRATEGIES OF QUALITATIVE DATA ANALYSIS:

Some of these are as follows:
A. Analytical Induction : Analytic induction is a way of building explanations in qualitative analysis by
constructing and testing a set of causal links between events, actions etc. in one case and the iterative
extension of this to further cases. It is research logic used to collect, develop analysis and organise the
presentation of research findings. It refers to a systematic and exhaustive examination of a limited number
of cases in order to provide generalisations and identify similarities between various social phenomena in
order to develop contacts or ideas. Its formal objective is causal explanation. It has its origin in the theory
of symbolic interaction which stipulates that a person’s actions are built up and evolve over time through
processes of learning, trial-and-error and adjustment to responses by others. This helps in searching for
broad categories followed by development of subcategories. If no relevant similarities can be identified,
then either the data needs to be re-evaluated and the definition of similarities changed, or the category is
too wide and heterogeneous and should be narrowed down. In analytical induction, definitions of terms are
not identified/determined at the beginning of research. They are rather, considered hypotheses to be tested
using inductive reasoning. It allows for modification of concepts and relationships between concepts
aimed at representing reality of the situation most accurately.
According to Katz, "Analytic induction (AI) is a research logic used to collect data, develop
analysis, and organize the presentation of research findings. Its formal objective is causal explanation, a
specification of the individually necessary and jointly sufficient conditions for the emergence of some part
of social life. AI calls for the progressive redefinition of the phenomenon to be explained (the
explanandum) and of explanatory factors (the explanans), such that a perfect (sometimes called
"universal") relationship is maintained. Initial cases are inspected to locate common factors and
provisional explanations. As new cases are examined and initial hypotheses are contradicted, the
explanation is reworked in one or both of two ways The definition of the explanandum may be redefined
so that troublesome cases either become consistent with the explanans or are placed outside the scope of
the inquiry; or the explanations may be revised so that all cases of the target phenomenon display the
explanatory conditions. There is no methodological value in piling up confirming cases; the strategy is
exclusively qualitative, seeking encounters with new varieties of data in order to force revisions that will
make the analysis valid when applied to an increasingly diverse range of cases. The investigation
continues until the researcher can no longer practically pursue negative cases."
Usually, three explanatory mechanisms are available for presenting the findings in analytical
induction as follows:

(b) Practicalities of action.

(c) Self-awareness and self-regard.
(d) Sensual base of motivation in desires, emotions or a sense of compulsion to act.

The steps of analytical induction process are as follows :

a) Develop a hypothetical statement drawn from an individual instance.
b) Compare that hypothesis with alternative possibilities taken from other instances. Thus the social
system provides categories and classifications, rather than being imposed upon the social system.
Progress in the social sciences is escalated further by comparing aspects of a social system with similar
aspects in alternative social systems. The emphasis in the process is upon the whole, even though
elements are analysed as are relationships between those elements. It is not necessary that the specific
cases being studied are “average” or representative of the phenomena.

According to Cressey, the steps of analytical induction process are as follows :

a) A phenomenon is defined in a tentative manner.
b) A hypothesis is developed about it.
c) A single instance is considered to determine if the hypothesis is confirmed.
d) If the hypothesis fails to be confirmed, either the phenomenon is redefined or the hypothesis is revised
so as to include the instance examined.
e) Additional cases are examined, and if the new hypothesis is repeatedly confirmed, some degree of
certainty about the hypothesis is ensured.
f) Each negative case requires that the hypothesis be reformulated until there are no exceptions.

B. Constant Comparison : Many writers suggest about the ways of approaching your data so that you
can do the coding of the data with an open mind and recognize noteworthy patterns in the data. Perhaps the
most famous are those made by the grounded theorists. This could be done through constant comparison
method. This requires that every time you select a passage of text (or its equivalent in video etc.) and code
it, you should compare it with all those passages you have already coded that way, perhaps in other cases.
This ensures that your coding is consistent and allows you to consider the possibility either that some of
the passages coded that way do not fit as well and could therefore be better codes as something else or that
there are dimensions or phenomena in the passages that might well be coded another way as well. But the
potential for comparisons does not stop there. You can compare the passage with those codes in similar or
related ways or even compare them with cases and examples from outside your data set altogether.
Previously coded text also needs to be checked to see if the new codes created are relevant. Constant
comparison is a central part of grounded theory. Newly gathered data are continually compared with
previously collected data and their coding in order to refine the development of theoretical categories. The
purpose is to test emerging ideas that might take the research in new and fruitful directions. In the case of
far out comparisons, the comparison is made with cases and situations that are similar in some respects but
quite different in others and may be completely outside the study. For example, still thinking about
parental help, we might make a comparison with the way teachers help students. Reflecting on the
similarities and differences between teaching and parental relationships might suggest other dimensions to
parental help, like the way that teachers get paid for their work but parents do not.
Ryan and Bernard suggest a number of ways in which those coding transcripts can discover new
themes in their data. Drawing heavily on Strauss and Corbin (1990) they suggest these include:
a. Word repetitions : Look for commonly used words and words whose close repetition may
indicated emotions
b. Indigenous categories (what the grounded theorists refer to as in vivo codes) : It refers to terms
used by respondents with a particular meaning and significance in their setting.
c. Key-words-in-context : Look for the range of uses of key terms in the phrases and sentences in
which they occur.

d. Compare and contrast : It is essentially the grounded theory idea of constant comparison. Ask,
‘what is this about?’ and ‘how does it differ from the preceding or following statements?’
e. Social science queries : Introduce social science explanations and theories, for example, to explain
the conditions, actions, interaction and consequences of phenomena.

f. Searching for missing information : It is essential to try to get an idea of what is not being done or
talked out, but which you would have expected to find.

g. Metaphors and analogies : People often use metaphor to indicate something about their key,
central beliefs about things and these may indicate the way they feel about things too.

h. Transitions : One of the discursive elements in speech which includes turn-taking in conversation
as well as the more poetic and narrative use of story structures.

i. Connectors : It refers to connections between terms such as causal (‘since’, ‘because’, ‘as’ etc) or
logical (‘implies’, ‘means’, ‘is one of’ etc.)

j. Unmarked text : Examine the text that has not been coded at a theme or even not at all.
k. Pawing (i.e. handling) : It refers to marking the text and eyeballing or scanning the text. Circle
words, underline, use coloured highlighters, run coloured lines down the margins to indicate
different meanings and coding. Then look for patterns and significances.

l. Cutting and sorting : It refers to the traditional technique of cutting up transcripts and collecting
all those coded the same way into piles, envelopes or folders or pasting them onto cards. Laying out
all these scraps and re-reading them, together, is an essential part of the process of analysis.
C. Triangulation ; According to Berg and Berg, triangulation is a term originally associated with
surveying activities, map making, navigation and military practices. In each case, there are three known
objects or points used to draw sighting lines towards an unknown point or object. Usually, these three
sighting lines will intersect forming a triangle known as the triangle of error. Assuming that the three lines
are equal in error, the best estimated place of the new point or object is at the centre of the triangle. The
word triangulation was first used in the social sciences as metaphor describing a form of multiple
operationalisation or convergent validation. Campbell and Fiske were the first to apply the navigational
term triangulation to research. The simile is quite appropriate because a phenomenon under study in a
qualitative research is much like a ship at sea as the exact description of the phenomenon in a qualitative
research is unclear. They used the term triangulation to describe multiple data collection strategies for
measuring a single concept. This is known as data triangulation. According to them, triangulation is a
powerful way of demonstrating concurrent validity, particularly in qualitative research. Later on, Denzin
introduced another metaphor, viz., ‘line of action’ which characterises the use of multiple data collection
strategies (usually three), multiple theories, multiple researchers, multiple methodologies or a combination
of these four categories of researcher activities. This is aimed at mutual confirmation of measures and
validation of findings. The purpose of triangulation is not restricted to combining different kinds of data
but to relate them so as enhance the validity of the findings.

Triangulation  is  an  approach  to  research  that  uses  a  combination  of  more  than  one  research 
strategy  in  a  single  investigation.  Triangulation  can  be  a  useful  tool  for  qualitative  as  well  as 
quantitative researchers. The goal in choosing different strategies in the same study is to balance them 
so each counterbalances the margin of error in the other.               

Used  with  care,  it  contributes  to  the  completeness  and  confirmation  of  findings  necessary  in 
qualitative research investigations. 
Choosing Triangulation as a Research Strategy
Qualitative  investigators  may  choose  triangulation  as  a  research  strategy  to  assure 
completeness of findings or to confirm findings. The most accurate description of the elephant comes 
from a combination of all three individuals' descriptions. Researchers might also choose triangulation 
to  confirm  findings  and  conclusions.  Any  single  qualitative  research  strategy  has  its  limitations.  By 
combining different strategies, researchers confirm findings by overcoming the limitations of a single 
strategy.  Uncovering  the  same  information  from  more  than  one  vantage  point  helps  researchers 
describe  how  the  findings  occurred  under  different  circumstances  and  assists  them  to  confirm  the 
validity of the findings. 

Types of Triangulation 
1. Data Triangulation : Time, Space, Person 
2. Method Triangulation : Design, Data Collection 
3. Investigator Triangulation 
4. Theory Triangulation 
5. Multiple Triangulation. which uses a combination of two or more triangulation techniques in 
one study. 
 

Each of these are described in detail in the following paragraphs 
 
1. Data Triangulation

According to Denzin (1989) there are three types of data triangulation: (a) time, (b) space, and (c)
person.

(a) Time Triangulation : Here, the researcher/s collect data about a phenomenon at different points 
in  time.  However,  studies  based  on  longitudinal  designs  are  not  considered  examples  of  data 
triangulation  for  time  because  they  are  intended  to  document  changes  over  time.  Triangulations  of 
data analysis in cross sectional and longitudinal research is an example of time triangulation.    

(b)  Space  Triangulation  :  It  consists  of  collecting  data  at  more  than  one  site.  At  the  outset,  the 
researcher must identify how time or space relate to the study and make an argument supporting the 
use of different time or space collection points in the study. By collecting data at different points in time 
and  in  different  spaces,  the  researcher  gains  a  clearer  and  more  complete  description  of  decision 
making  and  is  able  to  differentiate  characteristics  that  span  time  periods  and  spaces  from 
characteristics specific to certain times and spaces. 

(c) Person Triangulation : According to Denzin, person triangulation has three levels, viz., aggregate, 
interactive and collective. It is also known as combined levels of triangulation. Here researchers collect 
data from more than one level of person, that is, a set of individuals, groups, or collectives. Researchers 
might  also  discover  data  that  are  dissimilar  among  levels.  In  such  a  case,  researchers  would  collect 
additional  data  to  resolve  the  incongruence.  According  to  Smith,  there  are  seven  levels  of  ‘person 
triangulation’ as follows : 
i. The Individual Level.
ii. Group Analysis : The interaction patterns of individuals and groups.
iii. Organisational Units of Analysis : Units which have qualities not possessed by the individuals
making them up.
iv. Institutional Analysis : Relationships within and across the legal (For example, Court, School),
political (For example, Government), economic (For example, Business) and familial (For
example, Marriage) institutions of the society.
v. Ecological Analysis : Concerned with spatial explanation.
vi. Cultural Analysis : Concerned with the norms, values, practices, traditions and ideologies of a
culture.
vii. Societal Analysis : Concerned with gross factors such as urbanisation, industrialisation,
education, wealth, etc.

2. Methods Triangulation

Methods triangulation can occur at the level of (a) design or (b) data collection.   

(a)  Design  Level  Triangulation  :  Methods  triangulation  at  the  design  level  has  also  been  called 
between­method  triangulation.  Design  methods  triangulation  most  often  uses  quantitative  methods 
combined  with  qualitative  methods  in  the  study  design.  There  is  simultaneous  and  sequential 
implementation  of  both  quantitative  and  qualitative  methods.  Theory  should  emerge  from  the 
qualitative  findings  and  should  not  be  forced  by  researchers  into  the  theory  they  are  using  for  the 
quantitative  portion  of  the  study.  The  blending  of  qualitative  and  quantitative  approaches  does  not 
occur during either data generation or analysis. Rather, researchers blend these approaches at the level 
of interpretation, merging findings from each technique to derive a consistent outcome. The process of 
merging findings "is an informed thought process, involving judgment, wisdom, creativity, and insight 
and  includes  the  privilege  of  creating  or  modifying  theory”.  lf  contradictory  findings  emerge  or 
researchers  find  negative  cases,  the  investigators  most  likely  will  need  to  study  the  phenomenon 
further. Sometimes triangulation design method might use two different qualitative research methods. 
When  researchers  combine  methods  at  the  design  level,  they  should  consider  the  purpose  of  the 
research and make a logical argument for using each method. 

(b) Data Collection Triangulation : Methods triangulation at the data collection level has been called
within-method triangulation. Using methods triangulation at the level of data collection, researchers use
two different techniques of data collection, but each technique is within the same research tradition. The
purpose of combining the data collection methods is to provide a more holistic and better understanding of
the phenomenon under study. It is not an easy task to use method triangulation; it is often more time
consuming and expensive to complete a study using methods triangulation.

3. Investigator Triangulation 

         Investigator triangulation occurs when two or more researchers with divergent backgrounds and 
expertise  work  together  on  the  same  study.  To  achieve  investigator  triangulation,  multiple 
investigators  each  must  have  prominent  roles  in  the  study  and  their  areas  of  expertise  must  be 
complementary.  All  the  investigators  discuss  their  individual  findings  and  reach  a  conclusion,  which 
includes all findings. Having a second research expert examine a data set is not considered investigator 
triangulation.  Use  of  methods  triangulation  usually  requires  investigator  triangulation  because  few 
investigators are expert in more than one research method. 

4. Theory Triangulation 

              Theory triangulation incorporates the use of more than one lens or theory in the analysis of the 
same data set. In qualitative research, more than one theoretical explanation emerges from the data. 
Researchers  investigate  the  utility  and  power  of  these  emerging  theories  by  cycling  between  data 
generation and data analysis until they reach a conclusion. 
5. Multiple Triangulation  

       It uses a combination of two or more preceding triangulation techniques  in one study. 

Reducing Bias in Qualitative Data Analysis: 

Bias can influence the results. The credibility of the findings can be increased by:   

a. Using multiple sources of data. Using data from different sources helps in cross-checking the
findings. For example, combine and compare data from individual interviews with data from focus
groups and an analysis of written material on the topic. If the data from these different sources point to
the same conclusions, the findings are more reliable.

b. Tracking choices. The findings of the study will be more credible if others understand how the
conclusions were drawn. Keep notes of all analytical decisions to help others follow the reasoning.
Document reasons for the focus, category labels created, revisions to categories made and any
observations noted concerning the data while reading and re-reading the text.
c. Document the process used for data analysis. People often see and read only what supports their
interest or point of view. Everyone sees data from his or her perspective. It is important to minimise
this selectivity. State how data was analysed clearly so that others can see how decisions were made,
how the analysis was completed and how the interpretations were drawn.

d. Involving others. Getting feedback and input from others can help with both analysis and
interpretation. Involve others in the entire analysis process, or in any one of the steps. Have several
people or another person review the data independently to identify themes and categories. Then
compare categories and resolve any discrepancies in meaning.

Drawbacks to be Avoided: 
a. Do not generalise results. The goal of qualitative work is not to generalise across a population. Rather,
a qualitative data collection approach seeks to provide understanding from the respondent's perspective.
It tries to answer the question “why”. Qualitative data provide for clarification, understanding and
explanation, not for generalizing.
b. Choose quotes carefully. Use of quotes can not only provide valuable support to data interpretation but
is also useful in directly supporting the argument or illustrate success. However, avoid using people's
words out of context or editing quotes to exemplify a point. Use quotes keeping in mind the purpose for
including quotes. Include enough of the text to allow the reader to decide what the respondent is trying
to convey.
c. Respect confidentiality and anonymity when using quotes. Even if the person's identity is not noted,
others might be able to identify the person making the remark. Therefore, get people's permission to
use their words.
d. Be aware of, state and deal with limitations. Every study has limitations. Presenting the problems or
limitations encountered when collecting and analysing the data helps others understand the conclusions
more effectively.

Check Your Progress – II

Explain the meaning of the following terms :
(a) Analytical Induction :

(b) Constant Comparison :

 
 
 
 

(c) triangulation :
 
 
 
 
SUGGESTED READINGS

Bogdan R. B. and Biklen, S. K. Qualitative Research for Education: An Introduction to Theory and
Methods. Third Edition. Needham Heights, MA: Allyn and Bacon. 1998.

Miles, M. B. and Huberman, M. A. Qualitative Analysis : An Expanded Sourcebook. Thousand Oaks,

CA: Sage. 1994.

Katz, J. "Analytic Induction," in Smelser and Baltes, (eds) International Encyclopedia of the Social and
Behavioral Sciences. 2001.

Ragin, C. C. Constructing Social Research: The Unity and Diversity of Method. Pine Forge Press, 1994.

Strauss, A. and Corbin, J. Basics of Qualitative Research. Grounded Theory Procedures and Techniques.
Newbury Park, CA : Sage. 1990.
 12
 

RESEARCH REPORTING 
 

Unit Structure: 
  
12.0     Objectives 

12.1     Introduction 

12.2    Types of Research Report 

         12.2.1  Format 

         12.2.2  Style 

         12.2.3 Mechanism of report writing with reference to Dissertation and thesis and papers. 

12.3   Bibliography 

12.4   Evaluation of Research Report 

12.0 OBJECTIVES :  

After reading this unit, the student will be able to  

(a) Decide the style, format and mechanisms of writing a research report. 
(b) Write down bibliography correctly and comprehensively. 
(c) Explain how to write a research report.   
 

12.1 INTRODUCTION : 

  Educational  research  is  shared  and  communicated  to  others  for  dissemination  of  knowledge.  
After completion of research activities, the researcher has to report the entire activities that are involved 
in research process systematically in writing.  For clear and easy understanding of readers, writing a good 
research  report  requires  knowledge  of  the  types  of  research  reporting,  rules  for  writing  and  typing, 
format and style of research reporting and   the body of the report.  However, scholarship, precision of 
thought and originality of a researcher cannot be undermined in producing a good research report. 

12.2 TYPES OF RESEARCH REPORT : 

  Research reports mainly take the form of a thesis, dissertation, journal article and a paper to be 
prescribed at a professional meeting.  Research reports vary in format and style.  For example, there are 
difference found in a research report prepared as a thesis or dissertation and a research report prepared 
as a manuscript for publication. 

  The  dissertation  and  thesis  are  more  elaborate  and  comprehensive.  While  research  papers 
prepared for journal articles and professional meeting are more precise and concise. 

12.2.1 Format : 

Format  refers  to  the  general  pattern  of  organisation  and  arrangement  of  the  report.    It  is  an 
outline that includes sections and subsections or chapters and subchapters or headings and subheadings 
followed  to  write  research  report.    All  research  reports  follow  a  format  that  is  parallel  to  the  steps 
involved in conducting a study.  The format of a research report is generally well spelled out in contents.  
Different universities, institutions and organizations publishing professional journals follow style manual 
prepared on their own.  Some institutions follow by style manuals prepared by other professional bodies 
like  the  American  Psychological  Associations,  the  University  of  Chicago  and  the  Harvard  Law  Review 
Association.    The  Publication  Manual  of  the  American  Psychological  Association  (APA),  the  Chicago 
Manual  of  Style,  and  A  Uniform  System  of  Citation  (USC)  published  by  Harvard  Review  Association  are 
some of the worth mentioning style manuals that are followed by researchers to follow format and style 
while writing research reports.   

The  APA  format  is  widely  followed  because  it  eliminates  formal  footnotes.    It  provides  detailed 
information  about  research  format  for  all  types  of  research  reports  on  various  behavioural  and  social 
science disciplines.  The CMC presents guidelines for use of quotations, abbreviations, names and terms 
and distinctive treatment of words, numbers, tables, mathematics in type and writing footnotes.  Some 
historians and ethnographers prefer to use the CMC and USC. 
 

The  common  format  used  to  write  research  report  of  quantitative  studies  for  a  degree 
requirement is as follows. 

Preliminary pages  

1.  Title Page 

  a)  Title  

  b)  Degree requirement  

  c)  University or institution’s name 

  d)  Author’s name 

  e)  Supervisor’s name 

  f)  University Department 

  g)  Year 

2.  Acknowledgements 

3.  Supervisor’s Certificate 

4.  Table of contents 

5.  List of Tables 

6.  List of Figures 

Main Body the Report 

1.  Chapter – I : Introduction  

a. Theoretical Framework 
b. Rationale of the study  
c. Statement of the problem 
d. Definitions of terms 
e. Objectives 
f. Hypothesis  
g. Scope and Delimitations of the study 
h. Significance of the study   
2.  Chapter II : Review of Related Literature 

3.  Chapter III : Methodology and Procedures 
 a. Design and Research method  
b. Population and sample 
c. Tools and  techniques of data collection 
d. Techniques of data analysis 
4.  Data Analyses 

5.   Results and Discussions 

6.  Conclusions and Recommendations 

7.  Bibliography 

8.  Appendices  

  The common format followed for qualitative research including historical and analytical research is 
different from the format followed in quantitative research.  The common format used usually to write 
research report of qualitative studies for degree requirements is as follows. 

1.  Preliminary pages (same as in quantitative research) 

2.  Introduction 

  a)  General problem statement 

  b)  Preliminary Research Review 

  c)  Foreshadowed Problems 

  d)  Significance of the study  

  e)  Delimitations of the study 

3.  Design and Methodology 

a)  Site selection 

b)  Researcher’s Role 

c)  Purposeful / Theoretical Sampling   

  d)  Data collection strategies 

4.  Qualitative Data analysis and Presentation 

5.  Presentation of Findings : An Analytical interpretation  

6.    Bibliography 

7.  Appendices 

 
  The common format followed for writing a research report as an article or a paper for a journal 
and seminar is as follows : 

1.  Title and author’s name and address 

2.  Abstract 

3.  Introduction 

4.  Method 

  a)  Sample 

  b)  Tools 

  c)  Procedure 

5.  Results 

6.  Discussions  

7.  References 

Check Your Progress‐I 

1. What is the format of writing a dissertation? 

 
 

12.2.2 Style : 

  Style refers to the rules of spelling, capitalization, punctuations and typing followed in preparing 
the report.  A researcher has to follow some general rules for writing and typing a research report.  The 
rules that are applicable both for quantitative and qualitative research report are as follows : 

 
1.  The  research  report  should  be  presented  in  a  creative,  clear,  concise  and  comprehensive  style.  
Literary style  of  writing  is  to  be replaced  by  scientific  and  scholarly  style  reflecting  precise thinking.  
Descriptions should be free from bias, ambiguity and vagueness. Ideas need to be presented logically 
and sequentially so that the reader finds no difficulty in reading. 
2.  The  research  report  should  be  written  in  a  clear,  simple,  dignified  and  straight  forward  style, 
sentences should be grammatically correct.  Colloquial expressions, such as ‘write up’ for report and 
‘put in’ for insert should be avoided.  Even great ideas are sometimes best explained in simple, short 
and coherent sentences. Slang, flippant phrases and folksy style should be avoided. 
3.  Research  report  is  a  scientific  document  but  not  a  novel  or  treatise.    It  should  not  contain  any 
subjective and emotional statements. Instead, it should contain factual and objective statements. 
4.  Personal  pronouns  such  as  I  and  me,  and  active  voice  should  be  avoided  as  far  as  possible.    For 
example,  instead  of  writing  I  randomly  selected  30  subjects,  it  is  advisable  to  write  thirty  subjects 
were selected randomly by the investigator. 
5.  Sexist  language  should  be  replaced  by  non‐sexist  language  while  writing  research  report.    Male  or 
female  nouns  and  pronouns  (he  and  she)  should  be  avoided  by  using  plurals.  For  example,  write 
children and their parents have been interviewed rather than child and his parents were interviewed. 
6.  Instead of using titles and first names of the cited authors, last name is needed.  For example, instead 
of writing Professor John Dewey, write Dewey.  
7.  Constructed forms of modal auxiliaries and abbreviations should be avoided.  For example, shouldn’t, 
can’t,  couldn’t  should  not  be  used.    However,  abbreviations  can  be  used  to  avoid  repetition  if  the 
same has been spelled out with the abbreviation in parentheses.  For example, researcher can write 
NCERT if he/she has used NCERT in parenthesis in his/her earlier sentences like National, Council of 
Educational  Research  and  Training  (NCERT).There  are  few  exceptions  to  this  rule  for  well‐known 
abbreviations such as IQ. 
8.  Use of tense plays an important role in writing a research report.  Past tense or present perfect tense 
is used for review of related literature and description of methodology, procedure results and findings 
the study, Present tense is appropriate for discussing results and presenting research conclusions and 
interpretations.  Future tense, except in research proposals, is rarely used. 
9.  Economy  of  expression  is  important  for  writing  a  research  report.    Long  sentences  and  long 
paragraphs should be avoided.  Short, simple words are better than long words.  It is important that 
thought  units  and  concepts  are  ordered  coherently  to  provide  a  reasonable  progression  from 
paragraph to paragraph smoothly. 
10. Fractions and numbers which are less than ten should be expressed in words For example, six schools 
were selected or fifty percent of students were selected. 
11. Neither standard statistical formula not computations are given in the research report. 
12. Research report should not be written hurriedly.  It should be revised many times before publication.  
Even typed manuscripts require to be thoroughly proofread before final typing. 
13. Typing  is  very  important  while  preparing  research  report.    Use  of  computer  and  word  processing 
programme has made the work easy.  However, following rules of typography require to be followed. 
1
  i)  A good quality of hand paper  8 , by 11 in size and 13 to 16 pound in weight should be used. 
2
  ii)  Only one side of the sheet is used in typing. 

1
  iii)  The  left  margin  should  be  1   inches.  All  other  margins  i.e.  the  top,  the  bottom  and  the  right 
2
should be 1 inch. 

  iv)  All material should be double spaced. 

  v)  Times  New  Roman  or  A  Oldman  Book  Style  with  12  size  front  can  be  used  for  typing  words  in 
English and book titles can be italicized. 

  vi)  Direct quotations not over three typewritten lines in length are included in the text and enclosed 
in quotation marks.  Quotations of more than three lines are set off from the text in a double – 
spaced  paragraph  and  indented  five  spaces  from  the  left  margin  without  quotation  marks.  
However, original paragraph indentations are retained.  Page numbers are given in parentheses at 
the end of a direct quotation. 

Check Your Progress‐II 

1.  State the style in which a research report needs to be written. 

 
 

12.2.3 Mechanisms of Writing Dissertation and  Thesis : 

  In reality, the terms dissertation and thesis carry the same meaning. Thesis is an English (UK) term 
whereas  dissertation  is  an  American  term.  However,  in  India,  the  term  thesis  is  used  to  denote  work 
carried out for Ph.D. degree whereas the term dissertation is used to denote with work carried out for M. 
Ed. and M.Phil. degrees especially in theacademic discipline of Education. Both format or outlines stated 
earlier vendor format section. Thesis and dissertation should be complete and comprehensive. The main 
sections  of  a  dissertation  and  thesis  are  (i)  Preliminary  pages,  (ii)  Main  body  of  the  report  and  (iii) 
Appendices. 

i) Preliminary  pages  :  The  Preliminary  pages  include  title  page,  supervisor’s  certificate, 
acknowledgement  page,  table  of  contents,  list  of  tables  and  figures.  The  title  page  usually 
includes  the  title  of  the  report,  the  author’s  name,  the  degree  requirement,  the  name  and 
 location of the college or university according the degree and the date or year of submission of 
the report.  Name, designation and institutional affiliation of the guide are also written.  The 
title of a dissertation and thesis should clearly state the purpose of the study.  The title should 
be typed in capital letters, should be centred, in an inverted pyramid form and when two or 
more lines are needed, should be double spaced.  An example of the title page is given in the 
following box – 1. 
 

BOX‐1 

  DEVELOPMENT OF SCIENCE CONCEPTS IN HEARING IMPAIRED CHILDREN 
STUDYING IN SPECIAL SCHOOLS AND INTEGRATED SETTINGS 
 
 
 
Thesis submitted to the University of Mumbai  
   for the Degree of  

  DOCTOR OF PHILOSOPHY  

    in  

  ARTS (EDUCATION) 

 
 
By 
 

  As per the requirement of some universities and these include certificate of the supervisor under 
whose guidance or supervision the research mark was completed. 
 

  Most  theses  and  dissertations  include  an  acknowledgement  page.  This  page  permits  the 
researcher  to  express  appreciation  of  persons  who  have  contributed  significantly  to  the  completion  of 
the  report.    It  is  acceptable  to  thank  one’s  own  guide  or  supervisor  who  helped  at  each  stage  of  the 
research work, teachers, students or principals who provided data for the research and so on.  Only these 
persons who helped significantly for completion of research work should be acknowledged. 

  The table of contents is an outline of the dissertation or thesis which indicates page on which each 
major section (chapter) and subsection beings. 
 

  The list of tables and figures are given in a separate page that gives number, title of each table and 
figure and page on which it can be found.  Entries listed in the table of contents should be identical to 
headings and subheadings in the report, and table titles and figures, titles should be the same titles that 
are given to the actual tables and figures in the main body of the report. 
 

The  main  body  of  the  report  :  The  main  body  of  the  report  includes  introduction,  review  of  related 
literature, methodology and procedures, results and discussion, conclusions and recommendations and 
appendices.  The  introduction  section  includes  a  theoretical  framework  that  introduce  the  problem, 
significance of the study both from theoretical and practice points of view, description of the problem, 
operational definition of the terms, objectives, statement of hypotheses with rationale upon which each 
hypothesis  is  based  and  sometimes  delimitations  of  the  study.    The  problem  requires  to  be  stated  in 
interrogative statement or series of questions which answers are to be sought by the researcher through 
empirical  investigation.    Abstract  terms  and  variables  used  in  the  problem  require  to  be  operationally 
defined.    The  problem  should  be  stated  that  it  should  aim  at  finding  the  relationship  between  two 
variables. 
 

  The hypotheses related should be supported by the rationale deduced from the previous research 
studies or experiences with evidences.  Hypothesis which is a tentative answer to the research question 
should be stated concisely and clearly so that it can be tested statistically or logically with evidences.  An 
example of an hypothesis based on the rationale is given in the Box – 2. 

 
Box – 2  
 
Rationale – 1  
   

   Cognitive development possess through form successive stages from 
Piagian  perspective,  namely,  sensory  –  motor,  pre‐operational,  concrete 
  operational  and  formal  operational  stages.  Each  stage  starts  with  specific 
age  and  is  characterised  by  the  development  of  some  specific  concepts. 
  Hence, development of science concepts is related to age. It is assumed that 
age plays vital role in the development of concepts.  The hypothesis derived 
from this rationale is : 
 

The delimitation of the study should include such aspects as variables, sample, area or site, ratings 
tools and techniques to which the study has been delimited. 

  The second chapter of the main body of the report includes review of literature.  In this chapter, 
the  past  research  works  relating  to  the  present  study  under  report  should  be  described  and  analysed.  
The  description  that  includes  last  name  of  the  previous  researcher  with  year  of  study  in  parenthesis 
includes mainly method and findings briefly and precisely.  More description of studies and findings has 
no meaning unless those descriptions and findings are analsed critically to find out research gaps to be 
bridged  by  the  present  study.    Therefore,  it  is  required  that  after  description  of  the  previous  research 
work, the research report should contain a critical appraisal to find out significance the study. 

  

  The  methodology  and  procedure  section  includes  the  description  of  subjects,  tools  and 
instruments,  design,  procedures.    The  description  of  subjects  includes  a  definition  and  description  of 
population from which sample is selected, description of the method used in selecting sample and size of 
the sample, the description of population should indicate its size, major characteristics such as age, grade 
level, ability level and socio‐ economic status.  The method and sampling techniques used for selection of 
sample requires to be described in detail along with the size of the sample. 

  The  instruments  and  tools  used  for  investigation  require  detailed  description.    The  description 
includes the functions of the instrument, its validity, reliability and searing procedures.  If an instrument 
is  developed  by  the  investigator,  the  descript  needs  to  be  more  detailed  that  specifies  the  procedures 
followed for developing the tools, steps used for determining validity and reliability, response categories, 
scoring pattern, norms, if any, and guidelines for interpretations.  A copy of the instrument with scoring 
key  and  other  pertinent  information  related  to  the  instrument  are  generally  given  in  appendix  of  the 
dissertation and thesis but not given in the main body of the report. 

  The  description  of  the  design  is  given  in  detail.  It  also  includes  a  rationale  for  selection  of  the 
design. 

 
  The  results  section  describes  the  statistical  techniques  applied  to  data  with  justification, 
preselected  alpha  levels  and  the  result  of  each  analysis.    Analysis  of  data  is  made  under  subheadings 
pertaining  to  each  hypothesis.    Tables  and  figures  need  to  present  findings  (in  summary  form)  of 
statistical analysis in vertical columns and horizontal rows.  Graphs are also given in the main body of the 
report.  Tables and figures enable the reader to comprehend and interpret data quickly.  It is advisable to 
use  several  tables  rather  than  to  use  one  table  that  is  crowded.    Good  tables  and  figures  are  self  – 
explanatory.    Each  table  should  be  presented  on  the  same  page.    Large  tables  or  graphs  should  be 
reduced to manuscript page size either by Photostat on some other process of reproduction.  The word 
table or figure is centred between the page margins and typed in capital letters, followed by the table or 
figure number in Arabic numerals.  Tables and figures are numbered continuously but separately for each 
chapter..  Title of the table and figure is placed in double space below the word table and figure.  The title 
of  the  table  and  figure  should  be  brief  and  clear  indicating  the  nature  of  table  presented.    Column 
headings and row headings of a table should be clearly labeled.  If no data is available for a particular cell, 
indicate the lack by a dash (‐), rather than a zero (0). 

  Each table and figure is followed by description systematically in simple language with statistical or 
mathematical language in parenthesis.  An example in given in Box – 3. 

  Box – 3  

   

  TABLE  1  

   

  Z‐RATIO OF CONSERVATION RESPONSES OF HEARING IMPAIRED CHILDREN 
IN INTEGRATED EDUCATIONAL SETTING (IED) AND SPECIAL SCHOOLS 
  

  Concepts  Conservation of  Conservation of  Conservation of 

Mass  weight  volume 
 
setting  %  ‘z’ ratio  %  ‘z’ ratio  %  ‘z’ ratio 
 
IED Setting  86    43    11   
 
0 96 0 29 0 23
 

 
 

 
 

  The result emerged should be followed by discussion and interpretation.  Each result is discussed 
in terms of the original hypothesis to which it relates, and in terms of its agreement or disagreement with 
previous results obtained by other researchers in other studies.  Sometimes, researcher uses a separate 
section titled ‘Discussions’ where all the results emerged are explained either individually or joined both 
at micro level and macro level. 

  The conclusion and recommendation chapter includes description of the major findings, discussion 
of the theoretical and practical implications of the findings and recommendations for future research or 
future  action.    In  this  section,  a  researcher  is  free  to  discuss  any  possible  revisions  and  additions  to 
existing  theory  and  to  encourages  studies  designed  to  test  hypotheses  suggested  by  the  results.    The 
researcher may also discuss the implications of findings for educational practical and suggest studies that 
can be replicated in other settings.  The researcher may also suggest further studies to be designed for 
investing different dimensions of the problem investigated. 

  The  references  of  bibliography  section  of  the  dissertation  and  thesis  consists  of  lists  of  all  the 
sources alphabetically by author’s lost names that mere cited in the report. Most of the authors’ names 
were cited in the introduction and review of related literature, sections, Primary sources that are cited in 
the body of the dissertation and thesis are only included in the references. 

  Appendices are necessary in thesis and dissertation reports.  Appendices include information and 
data pertinent to the study which are not important to be included in the main body of the report or are 
too  lengthy.    Tests,  questionnaire,  career  letters,  raw  data  and  data  analysis  sheet  are  included  in  the 
appendices.    Sometimes,  subject  index  that  includes  important  concepts  used  in  the  main  body  of  the 
report.   The  list  of those  concepts  are  given  alphabetically  with  the  page  on  which  each  can  be  found.  
Appendices  are  named  alphabetically  followed  with  short  title  relating  to  the  theme.    (For  example, 
APPENDIX A Non‐verbal Text on concept attainment in Biology.) 

MECHANISM OF WRITING PAPERS : 

  Paper  includes  a  research  report  prepared  for  publication  in  a  journal  or  for  presentation  in 
seminar and professional meeting.  Paper prepared for journal and seminar follows the same mechanism 
of  writing,  style  and  format.  The  main  purpose  of  a  paper  is  for  sharing  the  ideas  emerged  with  other 
researchers,  which  is not  possible  through  dissertation  and  thesis.    The  content  and  format  of  a  paper 
and a thesis are very similar except that the paper is much shorter.  Lengthy thesis or dissertation may 
once again be prepared of two papers or articles.  The research paper follows the format given below. 

1.  Title 

2.  Author’s name 

3.  Abstract (About 100 to 120 words) 

4.  Introduction 

5.  Method 

6.  Results 

7.  Discussion  

8.  Reference 

  Writing of the title of a research paper follows the same mechanism it is followed in dissertation 
and thesis.  Below the title, author’s name and address is given.  

  An  abstract  of  the  paper  consisting  of  100  to  120  words,  and  containing  mainly  objectives, 
methods  and  findings  are  given  before  main  body  of  the  paper.    Other  preliminary  pages  of  the 
dissertation  and  thesis  are  not  required  in  the  research  paper  either  to  be  published  in  a  journal  or 
presented in a seminar. 

  The  introduction  section  of  a  research  paper  consists  of  a  brief  description  of  theoretical 
background,  agreements  and  disagreement  of  previous  researchers  on  findings  related  to  the  topic 
center report, objective, hypotheses. 

  The  method  section  deals  with  sample  size  and  sampling,  instruments  and  tools,  design  and 
procedure  of  collecting  data.    In  dissertation  and  thesis,  detailed  description  is  necessary,  whereas,  in 
research paper the same is to be writing very precisely and comprehensively. The author has to exercise 
judgment in determining which are the critical aspects of the study and which aspects require more in 
depth description. 

  The result section of a research paper includes tables and figures including graphs.  However, the 
tables and figures require to be described in the light of the hypothesis for its acceptance and rejection.  
The findings described should be supported by statistical values and alpha levels with mathematical signs 
of  less  than  (<)  or  greater  than  (>)  etc.  in  parenthesis.    For  example,  as  it  can  be  seen  in  table  1,  high 
creative and low creative teachers differed significantly on attitude towards class room teaching (t = 4.24; 
df = 121; p<.01), child centred practices (t = 2.14; df = 131; p<.05), educational process (t = 3.38; df = 131; 
p<.01)  and  pupils  (t  =  2.87;  df  =  131;          p  <.01)  in  favour  of  high  creative  teachers  as  mean  attitude 
towards class room teaching of high creative teachers is greater than their counterparts. 

  The discussion section is very important in a research paper.  Each finding is discussed in the right 
of  its  agreement  and  disagreement  with  the  previous  findings  followed  with  justification  based  on 
previous theory  and  existing  body  of  knowledge.    In  this  section,  the  researchers are  free  to  give  their 
critical  judgment  for  using  new  dimensions  that  were  emerged  out  of  the  study  in  order  to  add 
something new to the existing body of knowledge or for revision and modification of theory.  Critical and 
analytic description is highly essential in discussion.   

  Lastly,  names  of  authors  cited  in  the  paper  are  given  in  alphabetical  orders  beginning  with  first 
name in the reference. 

Check Your Progress‐III 

1.  Explain the mechanisms of writing a dissertation. 

 
 

 
 

 
12.3 BIBLIOGRAPHY : 

  A  bibliography  is list of  all  the  sources which  the  researcher  actually  used  for  writing a  research 
report.  Bibliography and references and sometimes used interchangeably, buy both are different from 
each  other.    References  consist  of  all  documents  including  books,  journal,  articles,  technical  reports, 
computer programmes and unpublished works that are cited in the main body of a research report.  i.e. 
dissertation,  thesis,  journal  article,  seminar  paper,  etc.  References  includes  mainly  primary  sources.  A 
bibliography, in contrast, contains everything that is either cited or not cited in the body of the report but 
are  used  by  the  researcher.    It  includes  both  primary  and  secondary  sources.    The  common  trend  has 
been to use bibliography in dissertation and thesis, and reference in journal articles and papers. 

  The  American  Psychological  Association  (APA)  Publication,  Manual,  the  Chicago  Manual  of  Style 
and Uniform System of Citation of Harvard Review Association are available that guide a researcher to 
write bibliography.  However, the APA style is widely used to write bibliography is educational research.  
It provides guidelines for writing different types of sources such as boxes, journal articles, unpublished 
dissertation  and  thesis,  unpublished  papers  presented  at  the  meeting  and  seminars,  unpublished 
manuscripts, technical reports etc. 

  Bibliography  is  arranged  in  alphabetical  order  by  the  last  names  of  the  first  authors.    When  no 
author  is  given,  the  first  word  of  the  title  on  sponsoring  organisation  is  used  to  begin  the  entry.    Each 
entry in the bibliography starts at the left margin of the page, with subsequent lines double spread and 
indented.  Extra space is not given between the entries. 

  Following illustrations provide information for writing different type of entries in the bibliography. 

1.  Book : 

  Vaizey, J. (1967).  Education in the modern world. New York : McGraw Hill. 

2.  Book with multiple authors : 

  Barzun, J. & Graff, H. F. (1977), The modern researcher, New York : Harcourt, Brace, Hovanovich. 

3.  Book in subsequent edition : 

  Hallahan, D.P. & Kauffman, J.M. (1982), Exceptional children (2nd ed.), Englewood Cliffs, NJ : Prentice 
Press. 

4.  Editor as author : 

  Mitchell, J. V., Jr (Ed.), (1985). Mental measurement yearbook (9th ed.), Highland Park, NJ : Gryphon 
Press. 

5.  No author given : 

  Prentice – Hall author’s guide. (1978), Englewood Cliffs, NJ : Prentice Hall. 

6.  Corporate or association author 

  American Psychological Association, (1983), Publication manual (3rd ed.), Washington, DC : Author 

 
7.  Part of a series of books : 

  Terman, L.M. & Oden, M.H. (1947), Genetic studies of genius series : Vol. 4. The gifted child grows up. 
Stanford, CA : Stanford University Press. 

8.  Chapter in an edited book : 

  Kahn,  J.V.  (1984),  Cognitive  training  and  its  relationship  to  the  language  of  profoundly  related 
children.  In J.M. Berg (Ed.), Perspectives and progress in mental retardation.  Baltimore : University 
Park, 211 – 219. 

9.  Journal article : 

  Seltzer,  M.M.  (1984)  Correlates  of  community  opposition  to  community  residences  for  mentally 
retarded persons.  American Journal of Mental Deficiency, 89, 1 – 8. 

10. Magazine article : 

  Meer, J. (1984, August), Pet theories, Psychology Today,                  pp. 60 – 67.   

11. Unpublished paper presented at a meeting : 

Schmidt, M., Khan, J.V. & Nucci, L. (1984, May), Moral and social conventional reasoning of trainable 
mentally retarded adolescents.  Paper presented at the annual meeting of the American Association 
on Mental Deficiency, Minneapolis, MN. 

12. Thesis or dissertation (unpublished) : 

  Best,  J.W.  (1948),  An  analysis  of  certain  selected  factors  underlying  the  choice  of  teaching  as  a 
profession.  Unpublished doctoral dissertation, University of Wisconsin, Madison. 

13. Unpublished manuscripts : 

  Kahn, J.V., Jones, C., & Schmidt, M. (1984).  Effect of object Preference on sign learnability by severely 
and  profoundly  retarded  children  :  A  pilot  study.    Unpublished  manuscript,  University  of  Illionois  at 
Chicago. 

  Kahn, J.V., (1991).  Using the Uzgiris and Hunt scales to understand sign usage of children with severe 
and profound mental retardation, Manuscript submitted for publication. 

14. Chapter accepted for publication : 

  Kahn,  J.V.  (in  press),  Predicting  adaptive  behavior  of  severely  and  profoundly  mentally  retarded 
children with early cognitive measures.  Journal of Mental Deficiency Research 

15. Technical report : 

  Kahn, J.V., (1981) : Training sensorimotor period and language skills with severely retarded children.  
Chicago, IL : University of Illinois at Chicago. (ERIC Document Reproduction Service, No. ED 204 941). 

 
12.4  EVALUATION OF RESEARCH REPORT : 

  Evaluation of a research report is essential to find out major problems and shortcomings.  Through 
a critical analysis, the student may gain some ideas into the nature of research problem, methodology for 
conducting  research,  the  process  by  which  data  are  analysed  and  conclusions  are  drawn,  format  of 
writing  research  report,  style  of  writing.    The  following  questions  are  suggested  to  evaluate  each 
components of research report. 
 

1.  The Title and Abstract 
• Are the tile and abstract clear and concise? 
• Do they promise no more than the study can provide? 
2.  The problem 

• Is the problem stated clearly? 
• Is the problem researchable? 
• Is background information on a problem presented? 
• Is the significance of the problem given? 
• Are the variables defined operationally? 
3.  The Hypothesis 

• Are hypotheses testable and stated clearly? 
• Are hypotheses based on sound rationale? 
• Are assumptions, limitations and delimitations stated? 
4.  Review of Repeated Literature 

• Is it adequately covered? 
• Are most of the sources primary? 
• Are important findings noted? 
• Is it well organised? 
• Is the literature given directly relevant to the problem? 
• Have the references been critical analysed and the results of studies compared and constructed? 
 

• Is the review well organised? 
• Does it conclude with a brief summary and its implications for the problem investigated? 
5.  Sample 

• Are the size and characteristics of the population studied described? 
• Is the size of the sample appropriate? 
• Is the method of selecting the sample clearly described? 
6.  Instruments and Tools 
 • Are data gathering instruments described clearly? 
• Are the instruments appropriate for measuring the intended variable? 
• Are validity and reliability the instruments discussed? 
• Are systematic procedure followed if the instrument was developed by one researcher? 
• Are administration, searing and interpretation procedures described? 
7.  Design and Procedure 

• Is the design appropriate for testing the hypotheses? 
• Are the procedures described in detail? 
• Are control procedures described? 
8.  Results 

• Is the statistical method appropriate? 
• Is the level of significance given? 
• Are tables and figures given? 
• Is every hypothesis tested? 
• Are the data in each table and figure described clearly? 
• Are the results stated clearly? 
9.  Discussions 

• Is each finding discussed? 
• Is each finding discussed in term of its agreement and disagreement with previous studies? 
• Are generalizations consistent with the results? 
10. Conclusions and Recommendations  

• Are theoretical and practical implications of the findings discussed? 
• Are recommendations for further action made? 
• Are recommendations for further research made? 
11. Summary 

• Is the problem restated? 
• Are the number and type of subjects and instruments described? 
• Are procedures described? 
• Are the major findings and conclusions described ? 
 

Check Your Progress‐IV 

1.  What are the criteria of evaluating a research report? 

 
 
 
 

Suggested Readings 

Turabian, K. Manual for Writers of Term Papers, Theses, and Dissertations. (7th ed.) Chicago: University 
of Chicago Press. 2007.  

Cardasco, F. and Gatner, E. (1958).Research Report Writing. New York : Barner and Noble.