Research Methodology

Dr Tamizharasi D
Professor
RV Institute of Management
Bangalore
Impact of Intrinsic Motivation
and Institutional Support on
Faculty Research Productivity
 Objectives of the Proposed Research

Objective1:
To identify the set of variables affecting Faculty Research Productivity (FRP).
Phase 1: To identify variables from the literature
Phase 2: To identify initial list of variables for FRP from Faculty’s perspective.
Phase 3: To propose an initial framework for FRP based on triangulation of phases 1 and 2.

Objective 2:
To examine the influence of Intrinsic Motivation on FRP.

Objective 3:
To examine the influence of Institutional Support on FRP.

Objective 4:
To develop a final conceptual framework for FRP influenced by Intrinsic Motivation & Institutional
Support based on the Initial Proposed Framework and Descriptive research.
Theoretical framework
• Basic steps:
• Identify and label the variables correctly
• State the relationships among the variables:
formulate hypotheses
• Explain how or why you expect these relationships
 Variables

Any concept or Main types of

construct that varies or variables:
changes in value • Dependent variable
• Independent variable
• Moderating variable
• Mediating variable
Dependent variable (DV)

• Is of primary interest to the researcher. The goal of the research

project is to understand, predict or explain the variability of this
variable.
• Ex: Research in behavioral finance has shown that overconfidence
can cause investors to underreact to new information.
• Dependent Variable?
Independent variable (IV)
• Influences the DV in either positive or negative way. The variance in
the DV is accounted for / explained by the IV.

• Ex: A marketing manager believes that selecting physically attractive

spokespersons and models to endorse their products increases the
persuasiveness of a message.
• Independent Variable?
Example
DV = f(IV)

Employee
Job Satisfaction
performance

IV DV
Affective
Organizational
Commitment
IV

Employee Performance = B1 Job Satisfaction + B2 Commitment

 Moderators
• Moderating variable
• Moderator is qualitative (e.g., gender, race, class) or
quantitative (e.g., level of reward) variable that
affects the direction and/or strength of relation
between independent and dependent variable.

Employee
Job Satisfaction
performance

Job Skill
Examples
• A manager of an insurance company finds that fear appeals
in commercials are positively associated with consumers’
behavioral intentions to insure their house. This effect is
particularly strong for people with a high inherent level of
anxiety.

10
Research Methodology
Research Design

Sampling Design
(Method, Size, Frame,
Units etc)
Data Collection Design
(Instruments,
Measurement &
Scaling)
Analytical Design
(Statistical tools &
Software to be used)
 Why Engineering Institutes?
Accreditation Research – Innovations,
process & quest Teaching nexus & Quality &
for outcome impact of faculty Competitiveness
based education research on student Development
learning outcomes

Why Karnataka?
Knowledge State Presence of 20000 Presence of a large
with 250 plus plus faculty in various number of R&D
engineering disciplines & a Centres in the field
institutes offering considerable number of core
degrees in various amongst them engineering, IT,
disciplines pursuing/pursued applied sciences
research. etc.
 Sampling Design
Approach of
Selecting the
Samples:

• Engineering Colleges in Karnataka stratified

Step 1: based on ownership/funding.

• Total Number of Faculty in Engineering

Step 2: Institutes in Karnataka determined.
[POPULATION]

Step 3: • Sample Size determined using Slovin’s formula.

• Sample Size determined in Step 3 to be divided

amongst engineering colleges based on proportion
Step 4: (%) of the strata determined in Step 1. Samples
randomly drawn at this stage.
Engineering Institutes in Karnataka
(Note: 5 and 6 included in 1 to 4; 7-AICTE considers it
as a separate classification for faculty. Thus 5, 6 and 7
classification excluded from the study)
Sl No Classification Number Final Total
1 Government Engineering Colleges 17
2 Aided Engineering Colleges 11 194
3 Private Engineering Colleges 147
4 Private / Deemed Universities 19
5 Minority Engineering Colleges 17* -
6 2nd Shift Engineering Colleges 11* -
7 Architecture Engineering Colleges 34* -
Total 256 194
•Sampling Method: Stratified Random Sampling for Selection of Colleges.
•Basis of Stratification: Classification of Engineering Colleges based on
Ownership/Funding – Dept of Technical Education, Government of Karnataka.
•https://dtek.karnataka.gov.in/page/Institutions/Engineering+Colleges/en
•Government Engineering Colleges: 17 (9%); Aided Engineering Colleges: 11 (5%);
Private Engineering Colleges: 147 (76%) Private/Deemed Universities: 19 (10%)
•Population: Total Number of Faculty in Engineering Institutes in Karnataka: 36, 862
•https://facilities.aicte-india.org/dashboard/pages/faculties.php
•Sample Size: Using Solvin’s formula n = N/1+Ne2 n-sample size; N-Population (36862)
& e-Error Margin (5%): 381
•Sampling Unit: Teaching Staff with PhD Qualification.
Type of Numbe Percentage Population Sample Size Breakup of Sample
Engineering r Size based on
Institute proportion of
institute type
stratified
Government 17 17x100/194 = 9% (381) = 34
9
Private 147 147x100/194 = 76% (381) = 290
76 36, 862 381
Aided 11 11x100/194 = 5% (381) = 19
5
Deemed 19 19x100/194 = 10% (381) = 38
Universities 10

Total 194 381

100
 Other considerations in Sampling Units / Categories /Scope
1. Branches / Departments – CSE, Mechanical & ECE
2. Designations – Assistant Professors, Associate Professors,
Professors.
3. Regions – Districts in Karnataka
4. Gender
5. Experience.
3. Data Collection Design
Data Collection Method:
• Primary Data (Questionnaire/Schedule , Focus Group Discussion &
Interview)
• Secondary Data (books, periodicals, newspapers and Internet
resources)
Measurement & Scaling techniques:
• Likert Scale
• Rank Order.
• Ratio & Interval Scales
 4. Analytical Design
I: To explore the relationship between Independent Variables
(Intrinsic Motivation & Institutional Support) and Faculty research
productivity; to examine the influence of one over the other:
a. Correlation analysis – Simple & Partial
b. Regression analysis – Multiple & Logistic.
c. ANOVA

II: To assess the most relevant factors causing a shift in research

productivity:
d. Factor Analysis (EFA and CFA)
e. Structural Equation Modeling
f. Path analysis.
Hypothesis
• A hypothesis helps to translate the research problem and
objective into a clear explanation or prediction of the expected
results or outcomes of the study.
• Hypothesis is derived from the research problems, literature
review and conceptual framework.
• Hypothesis in a research project logically follow literature review
and conceptual framework.
Hypothesis Development
• Good hypothesis:
• Must be adequate for its purpose
• Must be testable
• Can be:
• Directional
• Non-directional
Hypothesis Development

• A Proposition that is empirically testable. It is an

empirical statement concerned with the relationship

among variables.
• Is a logical relationship between two or more variables

expressed in the form of a testable statement.

Purpose of hypothesis
• To explain the relationship
• If advertising is increased, then sales will also go up.
• To establish the differences among groups
• More men than women are whistleblowers,
• To find the interdependence of two or more factors
• Working the night shift (as opposed to the day shift) is related to
whether or not one is married.
Directional and Nondirectional Hypotheses
• Directional hypotheses: the direction of the relationship between
the variables (positive/negative) is indicated.
• The greater the stress experienced in the job, the lower the job
satisfaction of employees. Or
• Women are more motivated than men are.
• Nondirectional hypotheses: there are no indication of the direction
of the relationships between variables.
• There is a relationship between age and Job satisfaction.
Null and Alternate Hypotheses
• The null hypothesis is a proposition that states a definitive, exact
relationship between two variables.
• That is, it states that the population correlation between two
variables is equal to zero or that the difference in the means of two
groups in the population is equal to zero (or some definite number).
• In general, the null statement is expressed as no (significant)
relationship between two variables or no (significant) difference
between two groups.
Null and Alternate Hypotheses

• The alternate hypotheses is the opposite of the null hypotheses,

is a statement expressing a relationship between two variables or
indicating differences between groups.
• The alternative statement is expressed as a (significant)
relationship between two variables or a (significant) difference
between two groups.
Difference between groups or means
• Independent sample T test
• Paired sample T test
• One way ANOVA
• Two way ANOVA
Difference between groups or means

Independent sample T test

• Compares the means between two unrelated groups on the
dependent variable(continuous)
• Your independent variable should consist of two
categorical, independent groups. 
• Ex: Gender (2 groups: male or female), employment status (2
groups: employed or unemployed)
• Ex: Salaries based on gender
Difference between groups or means

• Paired sample T test

• Compares the means between two related means
• Ex: Performance before and after training
• Alternate test: Wilcoxon signed rank test and McNemar’s test
One way - ANOVA
• To determine whether there are any significant differences
between the means of three or more independent (unrelated)
groups on a continuous dependent variable.
• Ex: Course(Beginner, Intermediate and advance) and Time
• Dependent variable should be measured at
the interval(Continuous)
• Independent variable should consist of two or more categorical
• The population variances in each group should be equal.
• Levene's Test for Homogeneity of Variances
• If the data is non-mormal -  Kruskal-Wallis H Test or Welsh test can be
used
Two – way ANOVA
• To understand the interaction between two independent variable
and on the dependent variable
• Ex: Gender, Education - Independent
Salaries - Dependent
• Independent variable should be categorical
• Dependent variable should be measured at the
interval(Continuous)
 To find associations between variables
• Pearson's correlation: Direction of relationship that exists
between two variables
• Ex: Stock return and Index return
• Spearman's correlation: Direction of association exists
between two ordinal variables
• Ex: A teacher is interested in whether those who do better at risk
management also do better in IFM
• Chi-square
• It is a test for independence, the chi-square test of association, is
used to discover if there is a relationship between two
independent categorical variables.
• Ex: Gender and preferred learning medium(online/offline)
Predicting scores
• Linear regression
• To predict the value of a variable based on the value of another variable
• The variable we want to predict is called the dependent variable or outcome
variable
• The variable we are using to predict the other variable's value is called the
independent variable or the predictor variable)
• There needs to be a linear relationship between two variables
• Ex: Exam performance and revision time
Stock return and index return
• Multiple regression
• Two or more independent variables, rather than just one, you need to
use multiple regression.
• Ex:Exam performance can be predicted based on revision time, attendance,
lecture, and gender