Research Methodology for Beginners

Module 4 : Methods of Data Analysis

Objective of the Module:

Select and explain the methods of data analysis

Knowledge Analysis:
Prerequisites: Essential Questions:

A student has Knowledge of : 1. What is data analysis and

1. Concept of research and why it is essential?

characteristics of research 2. How to analyze the

2. Types and steps of research qualitative and quantitative
data?

Instruction (Referencing):
Content Mode of Transaction
1. Analysis of qualitative data based on 1. Lecture with Presentation
various tools 2. Reading and reflective
thinking
2. Analysis of quantitative data and its
3. Assignment & Project
presentation with tables, graphs etc.
importance of quantitative data analysis
3. Statistical tools of data analysis-
measures of central tendency,
dispersion, relative position etc.

Dr. Mahesh M. Joshi 1 © SRTM University, Nanded

 Research Methodology for Beginners

Module 4 : Methods of Data Analysis

INTRODUCTION:

The Data analysis involves several activities like coding –decoding of data,
classification, organization, employing different tests on data, presentation of data
etc. The data analysis activities changes according to the qualitative and
quantitative nature of data.

The following are the main purposes of data analysis:

(i) Description: It involves the description of variables, constructs, observations to

meet the objectives of the research problem. a set of activities that are as essential
first step in the development of most fields. A researcher must be able to identify a
topic about which much was not known; he must be able to convince others about
its importance and must be able to collect data.

(ii) Construction of Measurement Scale: The researcher should construct a

measurement scale. All numbers generated by measuring instruments can be
placed into one of four categories:

(iii) Generating empirical relationships: Another purpose of analysis of data is

identification of regularities and relationships among data.

(iv) Explanation and prediction: Generally knowledge and research are equated
with the identification of causal relationships and all research activities are directed
to it.

Present module is comprised of two parts (i) Analysis of qualitative data and (ii)
Analysis quantitative data.

Analysis of Qualitative Data:

The qualitative data connotes the data in the form of text, Narrations, symbols and
non-numerical forms. The qualitative analysis is mainly descriptive analysis which
gives the explanation, conceptualization, theorization of etc. Few of the techniques
of the qualitative data analysis are as follows:

1. Typology: This technique involve the classification of data. The classes or

types must be very distinctive and broad which can involve large data as
possible.
2. Taxonomy: This is an advanced typology which defines the multiple levels
of the construct and hierarchy of the different types with their relationship.

Dr. Mahesh M. Joshi 2 © SRTM University, Nanded

 Research Methodology for Beginners

Module 4 : Methods of Data Analysis

3. Analytic Induction: It is the summarization of information according to

Inductive logic which begins with a hypothetical statement (major premise)
and then identifies the cases as evidences of major premise, looks the
exceptions to hypothesis and revises if found that the statement is not
applicable to the all cases.
4. Narrative Analysis: This technique involves the analysis of narrations may be
given in the text form or may be direct speech of the individuals. The
interpretation of the narration in the context of situation and
conceptualization from the narrations is major part of the narrative analysis.
5. Discourse analysis: This technique involves the analysis of content and
process of analysis of communication and interaction to find patterns,
categories, domains etc.
6. Event Analysis/Microanalysis: This technique involves the analysis of each
micro step or phase of any event, phenomenon or process from its beginning
point to the end to give explanations of structure and functioning of each
component involved in the event/process etc.

Analysis of Quantitative Data:

The quantitative data connotes the data in the numerical forms. The qualitative
analysis is mainly statistical analysis which have wide range of parametric and non-
parametric tests. Two types of statistics are supposed in quantitative data analysis
as :

1. Descriptive Statistics

2. Inferential Statistics

The descriptive statistics may be on any of the following forms:

A. Measures of Central Tendency: Central tendency describes how the data is

crowded and how the elements of data are close to each other. The
measures of central tendency mode, median and mean. The mode shows the
number having highest frequency in the data set, median shows the number
having relatively middle position in the data set and mean is mathematical
average of entire data set. Researcher should use appropriate parameter
according to the nature of data.

Dr. Mahesh M. Joshi 3 © SRTM University, Nanded

 Research Methodology for Beginners

Module 4 : Methods of Data Analysis

B. Measures of Variability: The variability shows the distribution of the data and
how the elements of data are separated from each other. The measures of
variation /deviation are range, mean deviation, quartile deviation and
standard deviation. Range shows the upper and lower limit of the data set,
quartile deviation is associated with median and shows the variation of the
data in four quartiles of the data set. Mean deviation and Standard deviation
are associated with mean. They show average of variation in entire data set.
Mean deviation is expressed as absolute value and standard deviation
formula uses the square values of the elements of entire data set.

C. Measures of Relative Position: Standard scores (Z or T scores), percentiles

and percentile ranks are the measures of relative position of particular data
within the entire data set.

D. Measures of Relationship: Measures of relationship shows how the two

variables are associated with each other and what the degree of their
relation is? Themeasures are Co-efficient of Correlation, partial correlation
and multiple correlations.

The inferential statistics has very wide range of different statistical tests. Few of
them frequently used are as follows:

Chi-square test

Chi-square test compares the frequency count of observations with expected count
of observations. The test may applied on the data of one independent variable or
may be used to compare distribution of multiple independent variables.

It is type of non-parametric test.

T-test

The t-test is employed to compare the two data set of independent variables. It is
ratio of the mean difference of two data set and standard error. The calculated t
value is compared with theoretical t value at particular degrees of freedom.

ANOVA (Analysis of Variance)

Dr. Mahesh M. Joshi 4 © SRTM University, Nanded

 Research Methodology for Beginners

Module 4 : Methods of Data Analysis

ANOVA is to compare more than two groups of data set or variables. It is the ratio
of error between the groups and within the groups. The ratio is called F value.
Calculated F value is compared with theoretical F value to find out significant
differences among the groups.

Regression Analysis:

Regression analysis is used to find out the relations among variables and the
direction of relationship also.

Two important criterions for testing are:

1. Degrees of Freedom: The degrees of freedom shows the number of

independent observations. Each statistical test has different formula to
calculate degrees of freedom.
2. Level of Significance (p value): Level of significance shows the degree of the
accuracy of the results within the boundary of 0- 100%. The concept is
based on Normal Probability Curve (NPC) of distribution of the data. Thus,
actual 0% and 100% could not be identified. Generally, the level of accuracy
must be 95 % or greater (which means p value=>0.05). p value =0.01
means 99% accuracy of the results.

Theoretical values of Chi square, t –value, F- value etc. at different level of

significance and degrees of freedom are given in the books of statistics
which are used to compare with calculated valuesw of above mentioned test.

Selecting your statistical test

The important things while selecting statistical tests are

The level of data (nominal, ordinal, ratio, or interval).

The number of groups or variables involved in the study
Nature of the data
Degrees of Freedom
Level; of Significance.

Dr. Mahesh M. Joshi 5 © SRTM University, Nanded

 Research Methodology for Beginners

Module 4 : Methods of Data Analysis

Now a day because of computer the analysis of large data is became smooth, easy
and more accurate. The different statistical packages for analysis of data belonging
various disciplines are available. For example, SPSS (Statistical Package for Social
Sciences) is popular for data analysis in the disciplines of social sciences.

SUMMARY:

Qualitative data analysis is significant for the study of problems having their
answers in the data in the form texts, symbols, non-numerical forms. There are
several techniques for analysis of qualitative data. However, it is not so simple or
mechanical.

Quantitative analysis is comprised of descriptive and inferential statistical

techniques. Descriptive statistics gives the knowledge of summarized features of
data by using different measures according to nature of data. Inferential statistics
is required to derive inference by using statistical tests for examination of
hypothesis.

Dr. Mahesh M. Joshi 6 © SRTM University, Nanded