Methodology on employee turnover
Research Design
A research design is the framework or plan for a study used as a guide in collecting and analyzing
data. To conclusively describe the factors influencing employee turnover in the Kenyan media
industry, case of Nationmedia Group, this study adopted a descriptive survey design to help
generate both qualitative and quantitative data. This design was appropriate because it helped
collect information about people’s attitude, opinion, and knowledge of certain phenomenon,
beliefs and habits (Mugenda, 1999). The survey research involved asking questions using a
questionnaire to senior managers, middle-level managers, and general staff, and obtaining
objective data therefore help explain the relationship between the independent and dependent
variables of the study.
Target Population
Target population refers to an entire group of individuals having common observable
characteristics (Mugenda and Mugenda 2003). Target population is the universal or absolute
population to which the researcher wants to generalize the results of the study . Therefore, the
target population of this study wasthree hundred and forty seven (347) subjects from Nairobi
Headquarters, comprising of thirty eight(38) senior managers,forty nine (49) middle-level
managers and two hundred and sixty(260) Junior staff.The target population was distributed as
shown in Table 3.1.
Table 3.1: Target Population
Category Population
Senior Managers 38
Middle-level Managers 49
JuniorStaff 260
TOTAL 347
Sample Size and Sampling Procedure
Sampling is the technique of selecting a representative form a target population with the purpose
of determining parameters of the whole population. (Kothari, 2007). Sampling procedures are
methods that are used to select an element from the population that will be included in the
sample.
Sample Size
According to Kothari (2004), a sample is a representative group of the accessible population that
is selected using various sampling methods. Kothari (2007) suggests that a researcher would have
to use at least 30% of the total target population as a sample size for it to be accepted as a good
representative sample. This study used30% of the target population as the sample. Thus, 104
repondents were selected from the target population as shown in Table 3.2.
Table 3.2: Sampling Frame
Category Population Sample (30%)
Senior Managers 38 11
Middle-level Managers 49 15
Junior Staff 260 78
TOTAL 347 104
Sampling Procedure
Sampling refers to the selection of a subset of individuals from within a statistical population to
estimate characteristics of the whole population. A stratified random sampling design wasused
where the research will pick every third person in each stratum. This technique was deemed ideal
for the study since the target population was heterogeneous and arrangable into strata as Senior
Managers, Middle-level managers and Junior Staff. According to Dempsey (2003), stratified
random sampling is a probability sampling technique wherein the researcher divides the entire
population into different subgroups or strata, then randomly selects the final subjects
proportionally from the different strata. The selected sample composed of staff members that
have at least six (6) months of work experience within NMG.
Data Collection Procedures
After consent is given by the Nation media Group to collect data, the researcher coordinated data
collection process after seeking permission from the Human Resource Office at the NMG
Headquarters. The study involved two research assistants to help in distribution of questionnaires
to the targeted respondents. The research assistants were taken through training to clearly
understand the research instruments, purpose of the study and ethics of research. The
questionnaires were administered to Senior Managers , Middle-level Managers ,and Junior
staffwho had at least six (6) months of work experience within NMG. A period of two weeks
was given to the respondents to complete the questionnaires.
Data Collection Instruments
Data was collected using semi-structured questionnaires that consisted of open and closed ended
questions. This method was deemed appropriate because the respondents were reached and were
able to read and write independently (Creswell, 2002).
Pilot Testing
The purpose of piloting of the research instrument was to test the appropriateness of the items to
the respondents in order to improve the instruments reliability and validity. This assistedin
refining the questionnaire, enhancing its readability, and minimizing the chances of
misinterpretation of the questions. It was administered to one (1) senior manager, one (1) middle-
level manager, and one (1) junior staff to help to check on the clarity and sustainability of the
wording in the questionnaires.
Validity of the Instrument
Mugenda and Mugenda (1999) define validity as the accuracy and meaningfulness of inferences
which are based on the research results. Validity is the degree to which results obtained from the
analysis of the data actually represent the phenomenon under the study. It is the correctness and
reasonability of data. Validity was ensured by discussing the instruments with the supervisor. The
accuracy of data to be collected largely depended on the data collection instruments in terms of
validity. Items on the questionnaire must measure something and a good questionnaire measures
what you designed it to measure. In this study, the instruments were reviewed by the research
supervisors and other research experts to ensure content validity.
Reliability of the Instruments
Reliability is defined as measure of the degree to which a research instrument yields consistent
results or data after repeated trials (Mugenda, 2003). Reliability also means the similar results are
obtained if the questionnaire is repeated soon afterwards with the same respondents. To establish
the reliability of the instrument, the test retest technique was used. It involved testing the
questionnaire with two (2) senior managers, two (2) middle-level managers and two (2) general
staff ,selected randomly but not in the study population. Responses from the test retest were
analysed using means, frequencies and percentages to produce score to help check whether the
two processes give similar results. If the discrepancy in scores between the two tests is high, the
instrument is said to yield data that has high test retest reliability.
A pilot study was conducted to pretest the validity and reliability of data collected using the
questionnaire before the main study. The reliability of the questionnaire was tested using
Cronbach's alpha value and the results were 0.72, 0.89, 0.78, 0.90, and 0.76 which averages to
0.81. This is rated as “Good” according to George and Mallery (2003) and is closer to 1.0
implying greater internal consistency of the items in the scale.
Data Analysis Techniques
Data is a collection of facts and figures relating to a particular activity under study (Shuttleworth,
2008). In addition, for data to be useful, it has to provide answers to the research questions. Data
analysis is defined as the whole process, which starts immediately after data collection and ends
at the point of interpretation and processing of results (Cooper and Schindler, 2000).
The data collected constituted both quantitative and qualitative data. Quantitative data was
analyzed using a Statistical software, SPSS by running frequencies, percentages, and correlation
to generate various relationships, frequencies and comparisons. Qualitative data was transcribed
and summarized to back up quantitative data. This largely depended on the data collection
methods and in line with the operationalization of variables table.
Ethical Considerations
Permission to carry out the study was sought from the Nation Media Group Human Resource
office and from the participants who participated in the study. The participants were assured of
anonymity; confidentiality and their ability to withdraw from the study at any time. No names or
person identification numbers were reflected on the questionnaires except the numbering of
questionnaires, which was done for purposes of identification of data during data editing.
6
Table Operationalization of Independent Variables
Objective Variables Indicators Measurement
Scale
Data Collection
Type
Tool of Analysis
To establish the influence of
job security on employee
turnover at NMG.
Independent
Variable: Job
security
Permanent and
pensionable
Temporary
Contractual
Ordinal, Questionnaire -Descriptive
statistics
-Percentages
-Frequency
table
-correlation
To assess the influence of
organizational justice on
employee turnover at NMG.
Independent
Variable:
Organizational
Justice
Job challenge
Communication
Trust
Supervision
Ordinal Questionnaire -Descriptive
statistics
-Percentages
-Frequency
table
-correlation
To determine the influence
of organizational culture on
employee turnover.
Independent
variable:
organizational
culture
Values
Vision
Beliefs
Behaviour
Unwritten rules
Ordinal, Questionnaire -Descriptive
statistics
-Percentages
-Frequency
table
-correlation
7
Objective Variables Indicators Measurement
Scale
Data Collection
Type
Tool of Analysis
To determine the influence
of the working conditions
on employee turnover.
Independent
variable: working
conditions
Equipment
Hours of work
Safety
Amenities
Ordinal , Questionnaire -Descriptive
statistics
-Percentages
-Frequency
table
To find out the relationship
between reward systems on
employee turnover
Independent
variable: reward
systems
Salaries
Gifts
Incentive
Bonus
Promotion
Ordinal , Questionnaire
-Descriptive
statistics
-correlation
-Percentages
-Frequency
table
Dependent variable:
employee turnover at NMG
Dependent variable:
employee turnover
at NMG
No. of employees
who have left the
last 5 years
Ordinal Questionnaire a) descriptive
statistics
b) percentages
c) frequency
tables
8
