Research consultancy
Methodology
CHAPTER THREE
METHODOLOGY
3.1 Introduction
This chapter outlines the research methodology employed to investigate the impact of information systems on the performance of government agencies in Uganda. It details the research design, area of study, target population, sample design, sample size, research instruments, measurement of variables, data collection procedure, data analysis, and ethical considerations.
3.2 Research Design
The study adopted a cross-sectional research design, which allowed for data collection from various sections of the population at a single point in time. This design was selected for its cost and time efficiency, as supported by Mugenda (2003) and Sekaran (2004). Both quantitative and qualitative approaches were utilized for data collection and analysis. According to Mugenda (2003), the combination of these methods minimizes bias, while Amin (2005) notes that triangulation provides a more comprehensive analysis by incorporating both inductive and deductive approaches, offering a multidimensional view of the findings. The qualitative approach further aids in understanding participants’ opinions, perceptions, and attitudes, providing deeper insights into the research problem.
3.3 Study Population
The study population consisted of 239 employees from the Uganda Revenue Authority (URA), including 1 Executive Director, 12 management staff, 40 Division Heads, 5 Regional Heads, and 181 staff members, all of whom had roles that influenced the impact of information systems on agency performance.
3.4 Determination of Sample Size
Using Krejcie and Morgan’s (1970) sample size determination table, a sample of 181 respondents was selected from a total population of 239 employees and 100 prominent taxpayers.
Table 3.1: Population and Sample Size of Respondents
| Category | Population Size | Sample Size | Sampling Technique |
|---|---|---|---|
| Executive Director | 1 | 1 | Purposive sampling |
| Managers | 12 | 12 | Purposive sampling |
| Division Heads | 40 | 38 | Purposive sampling |
| Regional Heads | 5 | 5 | Purposive sampling |
| Staff Members | 181 | 93 | Simple Random Sampling |
| Taxpayers | 100 | 32 | Simple Random Sampling |
| Total | 339 | 181 |
Source: URA Employee List (2013)
3.5 Sampling Techniques and Procedure
The study employed both probability and non-probability sampling techniques. Simple random sampling was used in probability sampling, while purposive sampling was used in non-probability sampling.
3.5.1 Simple Random Sampling
This technique gave every member of the population an equal chance of being selected, helping to avoid bias and ensuring simplicity (Neuman, 2006). It was used to select staff members and taxpayers.
3.5.2 Purposive Sampling
Purposive sampling was utilized to target respondents who had the most relevant knowledge about the research problem (Mugenda 2003; Neuman 2006). This method ensured efficient use of time and resources by focusing on key informants such as the Executive Director, Managers, Division Heads, and Regional Heads.
3.6 Data Collection Methods
Data collection involved three methods: questionnaire survey, interviews, and document review.
3.6.1 Questionnaire Survey
Questionnaires were used to capture respondents’ views on the study topic. Onen & Onen (2013) suggest that questionnaires offer respondents ample time to think about their responses, and the data can be referred to in the future. This method was used for staff members, Regional Heads, Division Heads, and taxpayers.
3.6.2 Interviews
Interviews provided qualitative insights into respondents’ feelings, opinions, and experiences related to information systems and their impact on government performance. Open-ended questions encouraged respondents to express their views freely, making this method suitable for the Executive Director and managers.
3.6.3 Documentary Review
The researcher reviewed relevant documents such as URA reports, journals, and publications to gather secondary data on the topic.
3.7 Data Collection Instruments
Various instruments were used in line with the data collection methods, including questionnaires, interview guides, and document review checklists.
3.7.1 Self-Administered Questionnaire
The questionnaire, composed of both closed- and open-ended questions, was designed to encourage respondent participation. It featured a 5-point Likert scale to gauge levels of agreement.
3.7.2 Interview Guide
An unstructured interview guide was used to collect qualitative data, allowing for more in-depth exploration of respondents’ insights, as recommended by Sekaran (2004).
3.7.3 Document Review Checklist
This tool facilitated the collection of secondary data by reviewing relevant documents and publications related to the study topic.
3.8 Data Quality Control
The study pre-tested the data collection tools on a smaller sample to ensure accuracy.
3.8.1 Validity
Validity was achieved through expert review, where supervisors and consultants from UMI assessed the instruments’ relevance to the study objectives. A Content Validity Index (CVI) of 0.82 was calculated, indicating high validity (Waner, 2005, as cited in Barifaijo et al., 2010).
3.8.2 Reliability
Reliability was tested using Cronbach’s alpha, with an overall score of 0.77, signifying acceptable internal consistency (Amin, 2005).
Table 3.3: Reliability of Research Instruments
| Variables | Alpha | Number of Items |
|---|---|---|
| Systems software | .808 | 9 |
| Systems infrastructure | .673 | 9 |
| User knowledge and skills | .840 | 11 |
| Financial performance | .670 | 3 |
| Customer satisfaction | .770 | 4 |
| Growth | .860 | 5 |
| Average | .770 | 41 |
3.9 Data Collection Procedure
The researcher obtained an introductory letter from the Uganda Management Institute (UMI) and sought permission from URA to administer questionnaires and conduct interviews. Respondents were informed that the study was for academic purposes, and their consent was obtained prior to participation.
3.10 Data Analysis
Both quantitative and qualitative data analysis methods were used.
3.10.1 Quantitative Data Analysis
Quantitative data were processed and analyzed using SPSS version 24.0. Descriptive statistics such as frequencies, means, and standard deviations were calculated, and correlation and regression analyses were conducted to test relationships between variables.
3.10.2 Qualitative Data Analysis
Qualitative data were analyzed using content analysis, where raw data were organized and evaluated for accuracy and consistency.
3.11 Measurement of Variables
A five-point Likert scale was used to measure respondents’ agreement with various statements related to the research variables, including information systems software, infrastructure, and user knowledge.
3.12 Ethical Considerations
The researcher ensured respondent confidentiality, sought informed consent, and communicated that the study was for academic purposes. Only selected respondents were given questionnaires or interviewed.