CHAPTER FIVE
RESEARCH DESIGN AND METHODOLOGY
This chapter presents the methodology that will be used to carry out this study. Research methodology is defined as an operational framework within which the facts are placed so that their meaning may be seen more clearly. The methodology includes the research design, population to be studied and sampling strategy, the data collection process, the instruments used for gathering data, and how data is analyzed and presented.
In this study a descriptive survey design will be used. Descriptive research portrays an accurate profile of persons, events, or situations (Robinson, 2002). It allows the collection of large amount of data from a sizable population in a highly economical way. It allows one to collect quantitative data, which can be analyzed quantitatively using descriptive and inferential statistics. Therefore, the descriptive survey is deemed the best method to fulfill the objectives of this study. The design is preferred because it is concerned with answering questions such as who, how, what which, when and how much, (Cooper and Schindler 2001). A descriptive study will be carefully designed to ensure complete description of the scenario, making sure that there is minimum bias in the collection of data.
Target population is the specific population about which information is desired. A population is a well defined or set of people, services, elements, events, group of things or households that are being investigated. The target population will consist of the following population: Top level management, middle level management and lower level management from Kenya Revenue Authority. The target is as follows:
| Population category | Target | Percentage (%) |
| Top level Management | 13 | 11 |
| Middle level Management | 97 | 81 |
| Lower level Management | 10 | 8 |
| Total | 120 | 100 |
3.4 Sample Design
The researcher will use stratified sampling procedure to select samples that are representative of the target population. This procedure is preferred since the entire target population has an equal chance of being selected. Mugenda and Mugenda (1999), point out that stratified sampling method ensures inclusion of small groups which otherwise could have been omitted entirely by other sampling methods. Thus the population will be divided into stratus. The sample is as follows:
Table 3.2 Sample Size
| Population category
(management) |
Target | Sample size
(50% of target) |
Percentage (%) |
| Top level | 13 | 7 | 11 |
| Middle level | 97 | 48 | 81 |
| Lower level | 10 | 5 | 8 |
| Total | 120 | 60 | 100 |
Source: Author (2013)
3.5 Data Collection Instrument and Procedures
Primary data will be used in this study. According to Ochola (2007), primary data refers to what is collected directly by the researcher for the purpose of the study. The data will be collected by the use of questionnaires and interviews. Research questionnaires having both structured and unstructured questions will be designed and administered. This enables the researcher to get vital data directly from the respondents. The researcher will interview the respondents in person and also through telephone using interview questions that will be both structured and unstructured; Interviews will ensure immediate feedback, accuracy, clarity and they will help reveal sensitive information. Interviews were used as a primary data collection technique.
This method is advantageous because of the direct feedback to the researcher. There is an opportunity to reassure respondent(s) should s/he be reluctant to participate, and the interviewer also clarifies certain instructions or questions. The interviewer also has the opportunity to probe answers by asking the respondent to clarify or expand on specific response(s). Finally, the interviewer can supplement the answers by recording his/her own observations, for instance; gender, time of day/place where the interview will take place.
3.5.1 Validity and reliability
Mugenda and Mugenda (2003) asserted that the accuracy of data to be collected largely depended on the data collection instruments in terms of validity and reliability. Validity as noted by Robinson (2002) is the degree to which result obtained from the analysis of the data actually represents the phenomenon under study.
Validity will be achieved by pre-testing the instrument to be used to identify and change any ambiguous, awkward, or offensive questions and technique as emphasized by Cooper and Schindler (2003). Reliability on the other hand refers to a measure of the degree to which research instruments yield consistent results (Mugenda & Mugenda, 2003). In this study, reliability will be ensured by pre-testing the questionnaire with a selected sample. The pre-test exercise will take place at the convenience of both the researcher and the research assistant
The data will be collected by use of questionnaires. Questions will be analyzed both qualitatively and quantitatively by first editing to get the relevant data for the study. The edited data will then be coded for easy classification and to facilitate tabulation. The tabulated data will then be analyzed by calculating various frequencies and percentages where possible. The collected Data will then be calculated by use of statistical inferences such as mean and mode where applicable. Presentation of data will be in the form of tables and figures.
3.7 Research Limitations
3.8 Research Ethics
