RESEARCH METHODS FOR TECHNICIANS

GST 05207

RESEARCH

The term research means to look for, examine, investigate or explore.

What is a research?
Various researches have defined research in different ways but all of them seem to have common
intersection that research is carried out to in order / with an intention of solving problem in
society or organization.
For example, research can be viewed as a directed and systematic study carried out to discover
facts needed to make appropriate decision. Thus, in order to make decision you need facts – and
you get facts through research.
On the other hand, research is serious study of a subject that is intended to discover new facts or
test new ideas (facts=data).
Others defined research as the systematic process of collecting and analyzing information
(data) in order to increase our understanding of the phenomenon about which we are concerned
or interested

More understanding on what is research?

 Research is a careful and process of inquiry to find answers to problem of interest.

 Research include: use of facts, use of theories, data (fact) analysis, sampling, doing and
experiment, going to library to read up on a topic.
 To do research is to investigate the problem systematically and thoroughly.
 Goal of research is to solve problem of interest.

Why Research method

 We carry out research in order to make decision accurately and appropriate

 To make our life easy and better through discovering new and better ways of solving
problem.
 Leedy (1993): Research powers the world by using researches who attempt to know
unknown and to do what was originally consider undoable. For example: discovering of
medicines

THE AIMS OF RESEARCH

1. To describe about a phenomena

2. To predict about something in the future
3. To explain about solution of problem
4. To interpret what is being investigated

IMPORTANCE OF RESEARCH

 To make appropriate decision

 To discover new ideas
 To make our life easy
 To provide skills and knowledge

RESEARCH METHODS vs. RESEARCH METHODOLOGY

 Research methods: Refers to the methods or techniques researches use in performing

research operation.
 Research methodology: it may be understood as a science of studying how research is
done scientifically. In it we study the various steps that are generally adopted by
researches in studying his research problem along with the logic behind.

The research process: characteristics and requirements

Research is a process for collecting, analyzing and interpreting information to answer questions.
But to qualify as research, the process must have certain characteristics: it must, as far as
possible, be controlled, rigorous, systematic, valid and verifiable, empirical and critical.
Let us briefly examine these characteristics to understand what they mean:

1. Controlled: Note that in life there are many factors that affect an outcome. A particular
event is rarely a result of a one-to-one relationship. Some relationships are more complex
than others. Most outcomes are interplay of a multiplicity of relationships and interacting
 factors. In the study of cause and effect relationships it is important to be able to link the
effect(s) with the cause(s) and vice versa. In the study of causation the establishment of
this link is essential. The concept of control means inexploring causality in relation to
two variables, set up a study in a way that minimizes the effects of other factors
affecting the relationship.

2. Rigorous: Be sure that the procedures applied to find answers to the questions are
relevant, appropriate and justified.

3. Systematic-the procedures adopted to undertake an investigation follow a certain logical

sequence.

4. Valid and justifiable-whatever you conclude on the basis of your findings is correct and
can be verified by you and others in the engineering field.

5. Empirical- any conclusions drawn are based upon hard evidence gathered from
information collected from real-life experiences or observations

6. Critical- critical scrutiny of procedures used and methods employed is crucial to a

research inquiry. The process of investigation must be foolproof and free from any
drawbacks. The process used and procedures used must be able to with stand critical
scrutiny.
TYPES OF RESEARCH
Types of research can be looked at from three different perspectives
1. Application of the finding of the research study
2. Objectives of the study
3. Mode of enquiry used in conducting the study

Application perspective
 Pure research
 Applied research
i) Pure research involves developing and testing theoriesand hypothesis
containing very abstract and specialized concepts having very broad
applications.

It is also concerned with development, examination, verification and refinement

of research methods, procedures, techniques, and tools that form the body of
research methodology, e.g.
 developing a sampling technique that can be applied to a particular
situation or
  developing a methodology to assess the validity of a procedure,
 developing an instrument say to measure the stress level in people,
 And developing the best way to measure people’s attitudes.

ii) Applied research means research which appliesresearch techniques,

procedures and methods developed in research methodology to collect
information about various aspect of a situation, issue, problem or phenomenon
so that information gathered can be used e.g. for policy formulation,
administration and enhancement of understanding of a phenomenon. Most
research is therefore applied in this sense.

Objective perspective
Any research can be broadly classified as being descriptive, co relational, explanatory or
explanatory.

i) Descriptive research describes a situation, problem, phenomenon, service or

program or provides information about say living conditions of a community, or
describes attitudes towards an issue, etc.

ii) Correlational studies attempt to discover/establish the existence of a

relationship/association/interdependence between two or more aspects of a
situation e.g.
o What is the impact of an advertising campaign?
o What is the relationship between stressful living and the incident of
heart attack?
o What is the relationship between fertility and mortality?
o What is the relationship between technology and unemployment?
o What is the effect of health service on the control of a disease, etc.
iii) Explanatory research attempts to clarify why and how there is a relationship
between two aspects of a situation/phenomenon. It tries to explain for example,
o why stressful living results in heart attacks
 o Why a decline in mortality is followed by fertility decline, or
o how the home environment affects children level of academic
achievement
iv) Exploratory research is done within the objectives of either to explore an area
where little is known or to investigate the possibilities of undertaking a particular
research study. When research is done to determine its feasibility it is also called
feasibility study or a pilot study. It is done when a researcher wants to explore
areas about which he has little knowledge or no knowledge. It is usually a small
scale study to determine if it is worth carrying out a detailed investigation. On the
basis of this study a full-scale study is done.

Mode of enquiry perspective

-Concerns the process you adopt to find answers to your research questions. Broadly there are
two approaches;

i) The qualitative research

A study is classified as qualitative if the purpose of the study is primarily to
describe a situation, phenomenon, problem or event; if the information is gathered
through the use of variables on qualitative measurement scale.
The analysis is done to establish the variation in situation, phenomenon or
problem without quantifying it.
- Description of an observation situation
- The historical enumeration of events
- A description of living condition
ii) The quantitative research
A study is classified as a quantitative if you want to quantify the variation in
phenomenon, situation, problem or issues. The information is gathered using
predominantly quantitative variables; if the analysis geared to ascertain magnitude
of the variation.
Examples:
-How many people have a particular problem?
 -How many people hold a particular altitude?

Both qualitative and quantitative approaches have their strengths and weaknesses, and
advantages and disadvantages, ‘neither one is markedly superior to the other in all respects’
The measurement and analysis of the variables about which information is obtained in a research
study are dependent upon the purpose of the study.

In many studies you need to combine both qualitative and quantitative approaches. For example,
suppose you want to find out the types of service available to victims of domestic violence in a
city and the extent of their utilization.
 Types of Research
From the view point of

Type of Information
Application Objectives
Sought

Exploratory Quantitative
Pure Research Research
Research

Discriptive Qualitative
Applied Research Research
Research

Correlation
Research

Explanatory
Research

RESEARCHETHICS
 These is code of conducting -> They tell us what is expected each other (a researcher)
 They play a big role in monitoring our behavior.
  As a student – one is expected to diligent in studies, punctual in attending classes,
submitting assignment.
 Similarly, there is a pattern of behavior expected from all of those in research.
Therefore research ethics refers to the appropriateness of your behavior in relation to the rights
of those who became the subject of your work.
 Researchers must ensure rights, privacy and welfare of the apple and communities that
form the focuses of their studies are safeguarded.
 As engineers there are certain behavior expected from you.
Respondent’s Ethics
 Being honest and truthful to research by providing accurate answers.
 It is unethical for respondent to falsify the answer so ask respondent to give the true
answer even though they think such answer will pain the researchers.
 As researcher

FORMULATION OF RESEARCH PROBLEM/ISSUE

 Research problem is a heart of any research. No research problem no research

 It is viewed as the question that has no answer yet, and it needs to be examined.
However person problems do not qualify as reseachable problem. The problem must
be common to many problems in organization/society that can be lead to decline of
productivity

Identification of a research problem /issue

Research starts with problem identification

Criterial of selecting a research problem /factors

 Interest and competance

 the significance of the proposed topic
 Availability of data-you will be able to access them
 Research guidelines of your institution

Some institution do nt allow you to carry a research outside your soecialization while
others do not care

 Your carreer goals: If you wish to be an expert in a certain subject

 Capable of being linked to theory

How to formulate a research problem

It should be clear stated and understood by anyone withouth further clarifiaction

Source of problems

 Reviewing literature
 Attending academic gathering; seminars, workshop and conferences
 Having exposure such as field study, practical training
 Consult experts and experienced researches in your area of study
 Discuss will colleagues
 Brainstorming
 Academic experience

Research Variables

Research variables are defined as factor or characteristics of interest that a researcher would like
to handle, observe, investigate or manipulate in the research process. e.g age, sex, business
perfomance, culture, political situation

According to research problem you may find that you are interested in many variables but it is
advised to pick few to make research manageable.

Types of variables

1. Independent variables
– also known as explanoty variables
-these are factors explain variation in the dependent variables (these are cause)
2. Dependent variables
-Usually there is only one dependent variable
-It is the outcome variable researcher is attempting to predict
 - Reseacher measure them to establish the change made on them.
3. Extraneous variables – these are independent variables which are likely to have effects on
dependent varibles but for some reasons are not to be measure by researcher.

THE RESEARCH PROPOSAL

To propose means, to put forward, suggest, intend or advice. Proposals therefore refer to
suggestions, intentions, plans or schemes.

A research proposal includes three main chapters

1. Introduction, consists
i. The background to the study
ii. Statement of the research problem
iii. Aims and objective of the study
iv. Hypothesis
v. Scope of the study
vi. Significance of the study
2. Review of the related literature
3. Research methodology
Other parts
4. References and appendices

Qualities of an effective proposal

An effective research proposal clear stated

 What is being proposed; what the project is about?
 How it will be carried out
 When it will be carried out
 How much it will cost

Research title

 It should be precise (words)

 It should be clear (conceptual)
  It should be specific (scope)
 It should be catchy (attractive)

Examples of writing good research title

Incorrect research problem

A study of implementaion of data mining techniques for effective crime and criminal
investigation.

Correct research problem

An implementation of data mining tecgniques for effective investigation of crime: A study of

Kahama and Chunya Districts.

Background of the study

 It intends to indicate where the problem lies

 Historical background of the problem needed to be captured well/origin of the problem
 The researcher tries to convince the reader that there is an issue/ problem that needs
solution.
 It shows the reader that the researcher knowns the study area as he/she is familiar with
what has preceded.

Statement of the problem

 It attempts to focus on the study by providing direction to the research.

 It indicates demarcation of the study
It indicates clearly that there is a problem that needed to be solved or a gape of
knowledge to be filled

Aims of the study

 Aims are intentions, goals or what researcher strive to achive.

 They are usually stated in general terms that are not easily measured

Importance of aims in reseach

  Aims reflect the outcome of the research
 Aims assist in formulation of objectives as they pinpoint of the purpose of the study
 Aims reflects the aspirations an expections of the reseacher
 Aims help in identifying whether the research is urgently needed or not

Research objectives

Objectives are intentions or purpose stated in specific measurable terms. They tell what the
researchers wants to achieve at the end of the study. They state specific tasks that will be carried
out by researcher to accomplish the aims of the study.

1. General objectives: formed a research problem

2. Specific objectives:substute the means by which the aims/goal of the study could
be achived.

Sample objective: Problem constraining industries in Tanzania

General Objectives: To examine/evaluate/estimate the problem constraining industies in

Tanzania.

Specific objectives

1. To asses the impact of availbility local materials in Tanzania on the level of product
produced
2. To estimate the loss incured by industries due to lack of reliable power supply in
Tanzania

Guidelines of writing objectives

The following are guidelines of writing specific objectives

 Reflection
Involves analyzing the aims of the study/topic and title before formulating specific
objectives. Specific objectives should relate to all these aspects.
 Formulation
 Researcher should write down the specific objectives ensuring that they are measurable
and if accomplishable should answer the reseach question
 Evalution
After the formulation of objectives, the researcher should attempt to answer the following
questions: Do the objectives address all parts of research problem? Do the objectives
mesures what is being researched? Are the objectives feasible? If too ambition, could the
scope of the study be reduced?

Sample objectives Kamonji (2003): An investigation of resources women farmers use to enhance
household food security : A case study of Embu district, Kenya

Specific objectives were to:

a) Determine he demographic chaacterics of the respondents

b) Determine the status of food availability in Embu district
c) Determine human and material resources women used to ensure food sufficiency
d) Determine the constraints women encounter in providing adequate foodfor their
household
e) Investigate how resources should be used efficiently to enhance household food security.

Research Hypothesis

Research hypothesis is defined as tentative prediction of the results, which are capable of being
tested usuing scientific methods. It involves independent and dependent vriables

Characteristics of reseach hypothesis

1. Should be clear and precises

2. Should be capable of being tested.
3. Should state relationship between variables
4. Should be specific and limited in scope
5. Should be stated in simple terms so that is easily understood by all concerned
6. It should be consistent with most known facts
7. Must explain the facts that give rise to the need for explanation
Importance of research hypothesis

 To guide the research and keep him in a right track

 Indicate the type of data required
 Indicate the type of data required
 It defines which facts are relevant and which are not.
 It indicates the scope of research /research boundaries
 It contributes to the theory development

Concept relating testing of Hypothesis

 Null hypothesis
 Alternative hypothesis

Null hypothesis

 It is denodet by Ho.
 It is stated in a negative form. It indicates that there is no relationship/difference between
variables
 Confirmation of the reseacher hypothesis is based on rejecting null hypothesis.

For example; if the reseacher wants to show that a difference exist in national examination
perfomance among students in public and private schools, then the researcher must prove that
there are no difference.

Other examples are:

Ho: - There is no significance difference between an individuals success in life and his/her
academic certificate

Ho: - Decline of industies in Tanzania is not due to raw materials

Ho: - Age and attitude to reading widely and extensively do not depend on each other

Ho:-There is no relationship between low income received by an employee and fraud

committed.
Alternative hypothesis is stated in positive/ is stated to indicate the actual expectation. It is
denoted by Ha.

-In research, the null hypothesis is tested , and if rejected, the alternative hypothesis is accepted.

Examples

Ha:-Decline of industies is a result of raw material

Ha: - Age and attitude to reading widely and extensively do not depend on each other

Ha:- there is a positive relationship between low income received by an

employee and fraud committed.

Research questions

 It depends on the nature of research because not allresearch proposals contain hypothesis
 In qualitative research, research questions replace hypothesis as means of interrogative
 Hypothesis are used in quantitative based research
 Research questions are used in qualitative research
 Depending on the nature of reseach. One can combine both research question and
hypothesis

Scope and limitation of the study

 It aims to indicate the boundaries or limits of the study in terms o contents, sample
geographical spread and the period to be covered by the study

Rationale/Significance of the study

 It is meant to show the importance of the study completed.

 Indicate beneficiaries and how are they going benefit with compiled findings

 Should have some ideas of the topic being investigated.

REVIEW OF THE RELATED LITERATURE

The literature means the works the researcher consulted in order to understand and investigate
the researcher problem. It involves examining documents such as books, magazine, journals and
dissertations that have a bearing on the study being conducted.

Importance of literature review in research

a. It sharpens and deepens the theoretical foundation of the research.

b. It gives the researcher insight into what has already been done in the selected field;
pinpoint its strengths and weakness.
c. It enables the researcher to know the kind of additional data needed in the study. This
helps avoid duplication of work
d. An understating the previous works helps the researcher to develop significant problem
which will provide further knowledge in the field of the study.
e. Wide reading exposes the researcher to a variety of approaches of dealing with research
issues.
f. It helps in developing an analytical framework or a basis for analyzing and interpreting
data.

Guidelines in formulating an effective literature review

a. Identify key issues to be addressed by literature review

- Like research topic, title, the relationship between independent and dependent
variables and objectives
b. Formulating a preliminary statement of the problem
-Helps the researcher to start to identify source of information relevant to the research
topic.
c. Identifying sources of information
Sources of information can be books, journals articles, conference proceeding,
government/corporate reports, magazine and newspaper, theses and dissertation.
d. Analyzed critically the articles identified
After identifying the articles to be used, the researcher should critically analyzed each
book or article selected by reflecting on the following
 -Has the author formulated a problem/issue? Is it clearly defined?
- Has the author evaluated the literature to the problem/issue?
-Is there an objective basis to the reasoning or is the author merely proving what he or
she already believes?
- How does the author structure the argument, for example, does it establish cause-effect
relationships?
- How does the book or article relate to the specific objectives or questions the researcher
is attempting to study?

e. Classify and code the article

-By taking notes and paraphrasing any relevant literature that the researcher would like to
include in the literature review. The researcher should mark with some codes for easy
retrieval. The details of the sources e.g. author, title date of publication, and the publisher.
f. Create an outline for the review
-By identifying main points
-By differentiating each main heading into logical subheadings. Points that are similar
should be grouped together.
g. Synthesize the information gatherer
- By analyzing each reference in terms of the research variables.
-By analyzing all references identified for the relationships or differences between them.
h. Write the review of related literature
Orodho (2003) indicates that in reviewing literature, the author should do the following
-Select studies that relate most directly to the problem at hand
-Tie together the results of the studies so that their relevance is clear
-Indicate that the research area reviewed is incomplete or requires extension
-Organize the review along major points relevant to the problem
Give the leader some indication of the relevant importance of the results from the studied
reviewed.

EVALUATION

After carrying out the review and writing, the researcher should reflect the following
 a. How effective was the information search?
-The researcher should reflect on whether the search was wide enough to ensure he/she
had found the relevant materials.
-The researcher should also reflect on whether the numbers of sources used are
appropriate in tackling the issue under discussion.
b. Has the literature used been critically analyzed?

The researcher should find out whether he/she has followed through a set of concepts and
questions, comparing items to each other. The researcher should find out whether instead
of just listing and summarizing items, he/she has assessed them, discussing their strengths
and weaknesses.
c. Will the reader find the literature review relevant, appropriate, and useful?
Research should reflect on the relevance of the information given to the readers.
d. Does the literature help to clarify the research problem?
The literature should help to help put the research problem into perspective.

Challenges faced in the formulation of literature review

a. Failure to connect the reviewed studies with the current study

b. Poor presentation
c. Large quantities of studies of review
d. Lack of documentation
e. Lack of referencing
f. Lack of critique
g. Failure to review current studies

RESEARCH DESIGN AND METHODOLOGY

Research methodology is organized under the following section; research design, research site,
population, sampling techniques, research instruments, data collection procedures and data
analysis.

RESEARCH DESIGN
A design is used to structure the research, to show how all of the major parts of the research
project work together to try to address the central research questions.

Aakeret et al (2002) defined a research design as the detailed blue print used to guide a research
study towards its objectives.

Orodho (2003) defined a research design as the scheme outline or plan that is used to generate
answers to research problem. Research design constitutes the blue print for the collection,
measurement and analysis of data (Kothari, 2003).

DESCRIPTIVE DESIGN

The major purpose of descriptive research is description of the state of affairs as it exists. The
researcher reports the findings. Kerlinger (1969) point out that the descriptive studies are not
only restricted to fact findings, but may result in the formulation of the important principles of
knowledge and solution to significant problems. They involve measurement, classification,
analysis, comparison and interpretation of data.

Descriptive survey is the method of collecting information by interviewing or administering a

questionnaire to a sample of individuals (orodho 2003). It can be used when collecting
information about people’s altitudes, habits or any variety of education or issues.

EXPERIMENTAL DESIGN

In this design, subject a randomly assigned to an experimental group which receives the
treatment or to a control group which does not receive treatment.

When an experiment design is employed, the researcher attempts to control/or manipulate the
variables in the study to establish the effects they create to the dependent variables. This can be
done by changing or holding variable(s) constant in experiment. The manipulated variable is
known as independent and the one we intend to observe or measure it effects is called dependent
variables. In short, the experimental research design intends to establish the cause and effect
relationship between an independent and dependent variables.

CORRELATIONAL DESIGN
This design enables the researcher to assess the degree of relationship between two or more
variables (Orodho 2003). For example you compare the examination performance of a group of
university students who prepare their own meals every day and those who eat at the cafeteria.

A CASE STUDY

A case study is an intensive description and analysis of single situation. Case studies involve in-
depth, contextual analysis of similar situations in other organization, where the nature and
definition of the problem happen to be experienced in the current situation

CROSS CULTURAL RESEARCH DESIGN

This is used to compare the behavior patterns of different cultures. Using this design you can
perceive how various cultures perceive certain education and social outcomes. For example you
can compare the performance of students in English in rural and urban schools to find out to
what extent cultural variations influence performance.

SURVEY STRATEGY

This is another strategy used by researchers to provide answers to business problems. Surveys
are credited for their usefulness in collecting a large amount of data from a sizeable population
for generalization effectiveness. The data in surveys are often obtained using standardized tools
particular questionnaire. Other structured methods such as structured interviews and observations
can also be employed. The biggest advantage of using survey designs is built on the external
validity of your results as generalized about findings are possible.

Guidelines in selecting research design

The following are essential researcher should adhere to while selecting a research design

a) Identify research questions to be address by the study. The researcher should identify and
reflect on the research questions raised in the study. Reflection should include
brainstorming on issues such as
 Do the questions raised in the study require collecting information by
interviewing or questionnaires? If the response is positive then the researcher will
use a survey design
  Do the questions raised in the study require systematic manipulation of
independent and dependent variables? If the answer is yes, then the researcher
will use experimental design.
 Does the study require the research to assess the degree of relationship between
two or more variables? If the answer is yes, then a correlation design will be used.
 Does the study seek to compare the behavior patterns of different cultures? If the
answer is positive then a cross cultural research design will be applicable.
b) After identifying the research design to be used, read materials related to that

design to understand its advantages and disadvantages.

RESEARCH SITES

The selection of a research site is essential. It influences the usefulness of the information
produced. The idea is to start with a large population and through progressive elimination, end
up with the actual where the data is collected (Orodho and Kombo, 2002).

Example of sample study allocation

Christobel Blinded Mission (CBM) Germany, the Ministry of Health, the Ministry of Eduction
and the local community and its leaders. The Makuru slum is an informal settlements area,
which has been in existences of the last 30 years. It covers an area of 14 squares kilometers. It is
continuation of the Kibera to Outer Ring Road in Embakasi.

POPULATION

Population (or universe) refers to the entire groupof people, events, institutions, and issues,

countries that is the target or subject of investigation.

Qualities of an effective population sample

 Diversity. The greater the diversity and differences that exists in the population sample

the higher the applicability of the research findings to the whole population

 Representative. It is important for the researcher to identify and select respondents that

fulfill the questions the research is addressing. For example if the study is on the effect of
 the slum environment of the basic education, it is important that the majority of the

population of the respondents is from the slum environment.

 Accessibility. An effective population sample is one that accessible to the researcher.

 Knowledge. An effective population sample should have some ideas of the topic being

investigated.

SAMPLING TECHNIQUES

Sample refers to any sub-set or sub-group of the population.

Sampling is the act, process or techniques of selecting a suitable sample, or a representative part

of population for the purpose of determining parameters or characteristics of the whole

population.

SAMPLING DESIGN (TYPES OF SAMPLING)

The term sampling design refers to that part of the research plan that indicates how cases are to

be selected for observation. Sampling designs are divided into two parts

a) Probability or random sampling

b) Non-probability or random sampling

SAMPLE SIZE

The exact number of the items selected from a population to constitute a sample. It

recommended using a large sample size to be able to generalize your findings. This is because

the large the sample sizes the lower the likely error in generalizing to population.

Probability sampling

 The key component behind all probability sampling is randomization, or random

selection
  Probability sampling is type of sampling where every member in the population has a

probability or a chance of being selected to form a sample. It is not biased in nature

Non-probability sampling

 Is a biased sampling procedure in that it does not provide any basis for estimating the

probability that each item in the population has a chance of being included in the

sample.

The various types of probability and non-probability sampling techniques are summarized in the

table below

Probability sampling Non-probability sampling

a) Simple random sampling a) Deliberate or judgement or purposive

b) Systematic random sampling sampling

c) Stratified random sampling b) Quota sampling

d) Cluster sampling c) Snowball sampling

e) Multi-stage sampling d) Conveniencesampling

PROBABILITY SAMPLING METHOD

SIMPLE RANDOM SAMPLING

 is a probability of sampling whereby all members in population have equal chance of

being selected to form a sample
 It is categorized into two parts; sampling with replacement and sampling without
replacement
 This method is referred to as simple random sampling as no complexities are involved
 Advantages of simple sampling are that the samples yield research data that can be
generalized to a large population.
  It permits the researcher to apply inferential statistics to the data and provides equal
opportunity of selection for each element of the population.

Disadvantages

 Bias in selection is common

 It is not the most statistically efficient method of sampling. The researcher may , just
because of luck draw, not get good representation of subgroups in population
 Some samples may be over or under represented
 Non response error is high. Some members selected may have moved to other areas.

SYSTEMATIC RANDOM SAMPLING

 Involves selecting the sample at regular intervals from the sampling frame, i.e,
every nth term.
 It is employed when both total population and sample size are known.
 The element of the population in the sample frame must be arranged in order, i.e
0,1,2,3 and so on. Then the required members from the list are chosen at a regular
interval after determine a starting point by using simple random sampling
techniques.
 This method is regarded as a complex random sampling because the element of
randomness is introduced by using random numbers to pick the first element to
start with.
 To determine the interval at which each member start will be drawn the following
formula is using
Total population
Interval=
Sample size

Advantages

 It is less tedious and more time saving when you have large population
 It saves cost in comparison to simple random sampling techniques.
  It also has a wide spread of the subjects over the population while in a
simple random sampling there is possibility of picking members which are
close together
 Bias is minimized
 Large population can be analyzed

Disadvantages

 The method has to be used in care because if there is a hidden periodicity in the
population, systematic sampling will prove failure.

STRATIFIED RANDOM SAMPLING

 is a sampling technique whereby the total population is divided into different

groups or layers before selection of representatives
 Those elements having similar characteristics are grouped into the same stratum
 The population can be divided into sub-population such as gender (male or
female), marital (married, single, divorce, widowed), age, occupation, level of
education, level of income, religion and sects or basing on other characteristics
depending on the nature of the study.
Advantages
 This method enables to represent not only the overall population, but also key
sub-group of population, especially small minority group.

Disadvantages

 If not careful stratified, bias can occur resulting in some groups of the population
being unrepresented

CLUSTER RANDOM SAMPLING

 The technique is, on the surface, similar to stratified sampling, as you need to divide the
population into discrete/ separate groups. However, it allows for the division of the study
 population into clusters (usually countries, provinces or other boundaries0 and random
sampling of everyone in those clusters.
 The units within the sample should be measure.
 The advantage of this method is that it needs a detailed sampling frame work for the
selected clusters only rather than for entire target area

Disadvantages

 There is a risk of missing on important sub-groups

 Lack of complete representation of the target population

MULT-STAGE SAMPLING

 Is also known as multi-stage cluster sampling

 It is used to overcome problems associated with geographically scattered

populations where face-to-face contact is needed or where it is expensive and time

consuming to construct a sampling for a larger geographical area (Saunderrs 2000)

 The method involves taking a series of cluster samples, each involving some form of
random sampling.

NON PROBABILITY SAMPLING0

PURPOSIVE SAMPLING

 In this sample method, the researcher purposely targets a group of people believe to be
reliable for the study
 Purposive sampling sometimes is known as judgment sampling because the decision with
regard to which element/item should be included or excluded in the sample rests on the
researcher judgement or intuition.
 Purposive sampling can be used with both quantitative and qualitative studies
 It is particularly relevant when you concerned with exploring the universe and
understanding the audience.
  This method is less expensive and quick for selecting sample but its major weakness is
bias. This because it is not upon the probability mode and hence the researcher does not
have a real basis for making inferences to a large population.

CONVENIENCE / ACCIDENTAL SAMPLING

 It involves selecting respondents primarily on the basis of their availability and

willingness of respond (Shaughness 2000).
 Respondents are people who just happen to be walking by, or show a special interest
in your research.
 The use of volunteers is an example of convenience sampling

QUOTAR SAMPLING

 This sampling begins by dividing the population into relevant strata such as age,
gender, martial, education, income or geographic area.
 The total sample is allocated among the strata in direct proportional to their estimated
or actual size of the population.
 Once a researcher identifies the people to be studies, they have to resort to haphazard
or accidental sampling because no effort is usually made to contact people who are
difficult to reach in quota.
 The problem of this method is that bias intrudes on sampling frame work. This is
because the researcher allowed self-select respondents.

SNOWBALL SAMPLING

 This method is employed when you’re not certain that respondents have relevant
information for your study, but you know a few of them. You will interview or provide
questionnaires to those few and then ask them to identify others who are likely to have
required data.
 Generally this method begins with a few people or cases and then gradually increases the
sample size as new contacts are mentioned by the people you started out with
RESEARCH INSTRUMENTS

Research instruments include the following

a) Questionnaires
–Questionnaire is considered in general terms to include all techniques of data collection
in which each person is asked to respond to the same set of questions in a predetermined
order
- It gathers data over a large sample
-It can be constructed into two main forms; open-ended questions and closed-ended
questions
b) Interviews- questions asked orally
c) Focused group discussion
-Usually composed of 6 – 8 individuals who share certain characteristics, which are
relevant to the study
-the discussion is carefully planned and design to obtain information on the participants’
beliefs and perceptions on defined area of interest.

d) Observation- provides information about actual behavior

DATA COLLECTION

 Data collection refers to the gathering of information to serve or prove some facts
 In data collection the researcher must have a clear vision of the instruments to be used,
the respondents and the selected area.
 Data collection is important in research as it allows for dissemination of accurate
information and development of meaningful programs.

METHOD OF COLLECTION OF DATA

a) Primary data
b) Secondary data

PRIMARY DATA

 Primary data is information gathered directly from respondents.

  Data is collected from the existing source
 It involves creating new data

Collection of primary data

i. Questionnaires
ii. Interviews
iii. Focused group discussions
iv. Observation
v. Experimental study

SECONDARY DATA

 Secondary data means data that is already available

 It involves gathering data that already has been collected by someone else

Secondary data may be available in;

a) Various publications of the central, state, or local governments

b) Various publications by foreign governments or international bodies and their
subsidiary organization
c) Technical and trade journals
d) Books, magazines and newspapers
e) Reports and published of various organizations connected with business and
industry, banks, Stock exchange etc.
f) Reports prepared by scholars, universities, economists in different fields
g) Public records and statistics, historical document and other sources of published
information.

DATA PROCESSING

 Data entry is part of data preparation before data analysis is attempted.

 Data entry aims at converting gathered data to a medium for viewing and manipulation
(Bhattacharyya, 2003)
  All gathered data in a questionnaire or interview guide are to be entered in computer to
facilitate tabulation and analysis.
 The key activities in data processing are editing, coding, classification and tabulation.

EDITING

 The researcher has to examine collected data (raw data) to identify errors and
omissions and to make necessary corrections
 The purpose of data editing is to secure quality standard on data.
 Editing involves inspection and if necessary correction of questionnaire or
observation form( Ghauri and Kjell 2002)
 Editing can be done while you are still in field with your respondents or after the field
study in your office.
 Field editing is recommended to clarify things which are not clear to you, such as
unreadable handwriting, abbreviations, unfilled questions, and sometime you might
have failed to get a clear meaning of statement.
 Failure to clear these kinds of uncertainties while still having access to your
respondent will cause a lot of trouble at the time of data analysis.

CODING

Coding refers to the process of assigning numerals or other symbol to classes.

Example

In your opinion which country will benefit than others in the new East-Africa Community?

 Tanzania 1
 Uganda 2 [ ]
 Kenya 3

Coding facilitates data entry because instead of entering the whole response like Tanzania, just a
number [1] or symbol (T) will serve the purpose.
CLASSIFICATION

 Classification is the process of putting response of the same characteristics into the same
group or class
 Data having the same traits are grouped together and therefore whole responses get
divided into a number of classes.
 The role of classification is to reduce the hugeness of collected raw data to facilitate easy
tabulation

Example

A researcher methodology instructor administers a test to his students amounting to 163. Ten
of them were absent during the test due to different reasons, and 153 students attempted the
test and their results were out after one week. The highest score was 96% and the lowest one
was 40%. The table below shows how the results of the test could have been classified
according to attributes (third column) and according to class-interval (second column).

Table 1: Classification of data according to attributes and class-intervals

No of students Classification according to Classification according to

class intervals attributes

20 90 -100 A
75 70 – 89 B+
28 60 – 69 B
17 50 – 59 C
13 40 - 49 D
Tabulation

 Tabulation is the process of summarizing raw data in a table to facilitate computation of

various measurements during data analysis.
 Data are arranged in the form of rows and columns by presenting the number of
frequencies falling into each of the several classes.
 It makes comparison possible and identification of errors easy.

Some principles of tabulation

 Insert a tittle to tell what the table is all table

 Number the table to facilitate easy referencing
 Indicate the source(s) of the data presented in the table just below the table to avoid
plagiarism.
 Do not overcrowd the table. Avoid unnecessary details in the table, instead use
approximation whenever possible.
 Indicate the units of measurement under each heading (e.g TZS, tonnes, kg etc)

DATA ANALYSIS

 Data analysis refers to examining what has been collected in a survey or experimental
and making deductions and inferences.
 It involves uncovering underlying structures; extracting important variables, detecting
any anomalies and testing and underlying assumptions.
 It involves scrutinizing the acquired information and making inferences.
 The process of analyzing aims at determining whether our observations support the
hypotheses we formulated before going into the field to collect the information, or reject
them.
 The main goal of data analysis is formulation of conclusion that can be used in decision
making in future situation.
 There two techniques of analyzing data; quantitative and qualitative techniques.
  The quantitative techniques are statistical in nature and are divided into descriptive
statistics and inferential statistics.

DESCRIPTIVE STATISTICS

 Descriptive statistics can be divided into two groups

a) Measures of central tendency
b) Measures of dispersion

Measures of central tendency

 Measures of central tendency are numbers that define the location of a distribution’s
center
 There are different measures of location/average, but most statisticians identifies three of
them to be most useful in research
a) Mean
b) Mode
c) Median

MEAN

 If the data from the sample , the mean is denoted by x

 If the data from the population, the mean is denoted by 
 Arithmetic mean – involves ungrouped data
- Arithmetic mean is obtained by adding all the data values and dividing by number of
items

Formula for sample mean x 

x
x i

For population mean

 
xi
N

where  denotes summation sign

N denotes the total number of items in the sample/population

xi denotes the value of 1st item x 1, 2, 3,  , N

 Grouped mean – involves grouped data

- Researcher is needed to find midpoint or model class in order to compute grouped
mean.
- The midpoint  m  of each class interval is multiplied by its frequency.

 lower class boundary + upper class boundary 

1
m
2

 fm
f
x i i

where by
f i mi denotes midpoint multiplied by its frequency

f i denotes the total number of classes

Example1
Find the sample mean of the following set of numbers 65, 63, 67, 69, 62, 60
Solution
Given

N  5 and x 
x i

65  63  67  69  62  60
x  64.3
6
Thus, the sample mean is 64.3
 Example 2

The 30 members of an orchestra were asked how many instruments each could play, the
result are set out in the frequency distribution. Calculate the mean number of instrument
played

Number of instruments, x 1 2 3 4 5

Frequency f 11 10 5 3 1

Solution

x f fx
1 11 11

2 10 20

3 5 15

4 3 12

5 1 5

f  30  fx  63

 fx  63  2.1
 f 30
x

MEDIAN

 The position average that divided a distribution into two equal parts

 If the data is arranged in ascending or descending order; in general the median is the

value that has half of the data values less than it, and half greater than it.
 If the sample size  n  is an odd number, the median is the middle value of the entire

population