CHAPTER III

RESEARCH METHODOLOGY
Introduction
This chapter provides an insight into the various methods and the procedures that will
be adopted in conducting the study. This chapter contains the research design,
population and sampling design, data collection methods, research procedures, data
analysis methods, reliability and validity, research ethics and finally, the chapter
summary.
Research Methodology is a process of gathering, recording, analyzing, and interpreting
the data. The basic objective of this study is to explore employee retention and to find
out the relation of retention and its components. For achieving the objective, the
following research methodology shall be followed in the course of conducting the
research.
Research Philosophy
Research is systematic, controlled, empirical, and critical investigation of hypothetical
propositions about the presumed relations among natural phenomena (Kerlinger, 2007,
p. 11). It is systematic and organized effort to investigate a specific problem that needs
a solution (Sekaran, 1992). It is undertaken not only to solve a problem existing in the
work setting, but also to add or contribute to the general body of knowledge in a
particular area of interest to the researcher (Wolf and Pant, 2007, p. 5). -19The possible purposes for doing research may be either one or more of the following
(Kothari, 2008): (i) to get research degree along with its consequential benefits; (ii) to
face the challenge in solving the unsolved problems, i.e., concern over practical
problems initiates research; (iii) to get intellectual joy of doing some creative work; (iv) to
provide service to society; and (v) to get respectability.
The basic criteria of good business/management research are as follows:

Purpose should be clearly defined and common concepts be used. Statements

should be short and direct,
Underlining relevant parts for better emphasis,
Pictures and graphs accompanying tables,
Graphics and animations accompanying the presentation of the report,
Procedure should be described in sufficient detail to permit another researcher to
repeat the research for further advancement, keeping the continuity of what has
already been attained.

Research Design

The research study is quantitative in nature; Quantitative data that was collected was
used to advance statistical analysis of the study. This study has utilized multiple
methodologies to achieve an optimum representative sample. The mix consists of
Cluster sampling, Stratified sampling, and simple random sampling. According to Cox
and Hassard (2005) a survey is a method of carrying out research using a structured
questionnaire that is given to a sample of a population and designed to elicit specific
information from the respondents. The survey questions are designed to gather
information on things such as attitudes, intentions, awareness, behaviors and
motivations. The data is collected in the form of questionnaire, which were filled by
employees working at different levels of management in LUMS University. In the
questionnaire, factors will be covered that are in accordance with the motivational
concern such as Job description, Appraisals, defined tasks, Salary, Work satisfaction,
Environment etc. The variables used in Questionnaire are in continuation with the work
done by (Safakli and Ertanin 2012).The variable covered in our questionnaire are
divided into two major categories; Motivational Factors and Hygiene factors, each
category will be used to take necessary information from the respondent and it will be
easy for the researcher to calculate and eliminate the non-response rate and the
irrelevant questionnaires filled by LUMS Employee.
Population and Sampling Techniques
According to Cooper and Schindler (2008), population is defined as the total collection
of elements under study whereby references have to be made. Our population was the
employee of LUMS There are total 3 department which play their role in LUMS they are
HR, Admin, Accounts information. And in this study we cover all these departments.
In a research study, sampling is defined as the process of selecting respondents for a
study in such a way that the respondents selected are a representative of the whole
population (Mugenda & Mugenda 2003). Sampling procedure may be defined as a
systematic process of individuals for a study to represent the larger group from which
they are selected (Cooper and Schindler, 2008). They all define a sample as the method
of selecting a portion of the population for conducting a study in order to represent the
population adequately since it is impossible to take the entire population because of
time, financial factors and errors which can discourage the researcher and lead him to
surrender the study. This study has utilized multiple methodologies to achieve an
optimum representative sample. The mix consists of Cluster sampling, Stratified
sampling, and simple random sampling.
The sampling process was to be guided by the parameters in the population in line with
specific objectives of the study (Cooper and Schindler, 2011). The study adopted

Cluster sampling, Stratified sampling, and simple random sampling to ensure that every
one had an equal chance of being sampled, and also to ensure that different age
groups were represented. Semi-structured questionnaires were then administered to
obtain the necessary data.
According to Cooper and Schindler (2008), sample size is described as a smaller set of
elements from the larger population. Mugenda (2003) argued that the choice of sample
size is governed by the confidence you need to have in your data, level of certainty, the
accuracy you require for any estimates made in your sample, the type of analysis you
are going to undertake and finally the size of the total population from which your
sample is drawn. Our sample size was 150.
Research Procedures
Research procedures refer to a detailed description of the steps to be taken and the
conduct of research should be provided for by the purpose of the study. A pilot test
involving 10 respondents was carried out to check the validity, clarity and reliability of
the contents of the questionnaire. A pilot test was conducted for the study to detect
whether weaknesses in design and instrumentation existed, and to provide data to
measure reliability and validity of the study. According to Saunders et al., (2009) a
complete account of the research process including pilot testing, scheduling of the
subjects and selection of the data collection instruments has to be conducted.
After the questionnaire was developed, it was subjected to a pilot test within one of that
department whose employees were not taking part in the survey.
Data Collection Methods
Data collection is the process of gathering and measuring information on variables of
interest, in an established systematic fashion that enables one to answer stated
research questions, test hypotheses, and evaluate the outcomes (Cooper and
Schindler, 2008). The primary data collection method was carried out by the use of
questionnaires. This was accomplished by approaching employees within sampled
departments, explaining the objective of the research and handing them the
questionnaire to fill. Secondary data was easy to collect and review accordingly. But
some of the websites were not accessible as they require paying certain amount of
money to give access. So, to fulfil this need, primary data served best to the purpose.
Through primary data the author has come to know about some of the details of
variables considered in the study and their prior studies were not accessible because of
some limitations. So researcher has gathered primary data to resolve the issue and in
this regard questionnaire was used as tool of data collection. This instrument was
developed in accordance to the study objectives so that relevant and accurate data can
be collected.

Data Analysis Methods

Data analysis that was conducted involved reducing the collected data to a manageable
size, by developing summaries, through the utilization of data analysis techniques
(Cooper and Schindler, 2008). The quantitative data was analyzed using both
descriptive and inferential statistics. Descriptive statistics was utilized for measures of
central tendencies (Mean, Median and Mode), and measures of dispersion (Variance,
Standard deviation, Standard Error, and Percentiles). On the other hand inferential
statistics was utilized for correlations, linear and multiple regression. Linear regression
was used on factors that indicated significant correlation. Multiple regression was then
administered to the list of factors that had indicated significant correlation with employee
turnover. The multiple regression model used was: Y= 0 + 1X1 + 2X2 + 3X3+ e.
Regression was done to determine the level of significance when the factors are
combined. The analysis process entailed the transformation of raw data into Tables, and
charts, containing frequency distribution and percentages that provided answers to the
research questions. In order to analyze data, appropriate tools and techniques shall be
used. Statistical tools like average, standard deviation, coefficient of standard deviation,
correlation shall be used. Appropriate financial tools, like ratio analysis, shall also be
used. SPSS program shall be extensively used to analyze and interpret data. Tables,
charts, graphs, pie charts etc. shall be used whenever required to exhibit and analyze
the data.
Reliability and Validity
Reliability is the degree of consistency between two measures of the same thing
(Mehrens and Lehman, 1987). The measure of how stable, dependable, trustworthy,
and consistent a test is in measuring the same thing each time is reliable (Worthen et
al., 1993). It is the extent to which a test or any measuring procedure gives the same
result on repeated trials in similar circumstances.
Reliability refers accuracy and consistency measuring device. We can use suitable
method for reliability of research. Wolf and Pant (2007) suggest the reliability of the
measurement may be obtained by one of the three methods: (i) test-retest or the
repetition of the same measure; (ii) Alternative measurement forms or giving another
form of the measure deemed to be equivalent, and (iii) Spilt-half or dividing a
measurement into at least two equivalent parts Gibs (2007) suggests following reliability
procedures:

Check transcripts to make sure that they do not contain obvious mistakes made
during transcription.
Make sure that there is not a drift in the definition of codes, a shift in the meaning
of the codes during the process of coding. This can be accomplished by

constantly comparing data with the codes and by writing memos about the codes
and their definitions.
For team search, coordinate the communication among the coders by regular
documented meetings and by sharing the analysis.
Cross-check codes developed by the different researchers by comparing results
that are independently derived.

Validity is the extent to which certain inferences can be made from test scores or other
measurement (Mehrens and Lehman, 1987). It is the degree to which they accomplish
the purpose for which they are being used (Worthen et al., 1993). There are three kinds
of validity. They are as follows (Wolf and Pant, 2007):

Content validation involves assessing the representativeness or sampling

adequacy of the items contained in the meaning of the instrument.
Construct validation involves understanding the meaning of the obtained
measurements.
Criterion-related validation involves inferring an individuals score or standing on
some measurement, called a criterion, from the measurement at hand

Credibility, transferability, dependability and conformability (Trochim, 2008) are the

elements of reliability and validity of the study. Credibility refers believable from the
viewpoint of the participant in the research and transferability refers to generalized
ability to other context. Similarly, dependability refers replicable ability of the research in
other subjects and conformability refers the degree to which the result could be
confirmed.
Factors like- methods of data collection, tools and models of analysis, testing,
interaction, response of respondents, bias of researcher etc. directly affect in the validity
and reliability of the study. The study will take into account strictly these factors and will
commit in testing and using relevant instruments and models. Only trustworthy sources
will be used in the course of action and the role of researcher will be mentioned in the
study.
Research Ethics:
Pratt (2006) stated that, the main ethical debates in quantitative is practices that might
be extremely unobtrusive, such as observing through a one-way mirror, concealed taperecording or telephone-tapping are just not permissible - and might lead to criminal
proceedings. This study will fully considered the ethical matters of the organizations.
The study will observe the non-negotiable value of honesty and fairness. Respect for
persons will be maintained properly.

Chapter Summary
This chapter presents the various methods and procedures that were adopted in
conducting the study in order to answer the research questions raised in the first
chapter. The chapter was organized in the following ways: the research design,
population and sample, data collection methods, sampling design and sample size,
research procedures and data analysis. The next chapter presents the results and
findings of the study.