CHAPTER THREE
RESEARCH METHODOLOGY
3.0 Introduction
This chapter explains various methodologies that were used in gathering data and analysis which
are relevant to the research. The methodologies will include areas such as the location of the
study, research design, sampling and sample size, types of data, data collection method and its
management.
3.1 Research Design
This study descriptive research design is defined as a research method that describes the
characteristics of the population that is being studded. As was used where data was collected
from the respondents at one point in time. This design always focuses more on what of the
research subject rather than the why of the research subject (Babbie, 1990). The data for this
survey was further collected at the operating point of TANESCO.
3.2 Area of Study
The study was carried out in Meru district, Arusha city. The rationale behind this choice is from
the sense that Arusha is a metropolitan city where all necessary offices, relevant institutions in
the country are situated and their operations are based in the other mentioned regions. Hence,
there is a possibility of obtaining all necessary and relevant data from these offices.
3.3 Research Approach/ Strategy
There are two types of research approach according to Kombo (2006) i.e. quantitative approach
this technique uses numerical data or data that are quantified and Qualitative approach that uses
non-numerical data or data that have not been quantified. The researcher use this for nonstandardized data based on meanings that need to be expressed through words such as
managerial decisions. The researcher combined both, quantitative approach and qualitative
approach in analyzing the data collected. The reasons is due to the fact that some findings needed
personal assessment of the information obtained from consumers, while some conclusions
reached after doing simple mathematical computations such as mean, percentages and
tabulations.
3.4 Population of the Study
Population of the study means covers all the cases of individuals or things or elements
that fit a certain specification i.e. all the items under consideration in any field of inquiry
constitute. The population for this study was about 60 respondents, which will includes
customers of electricity, scholars and employees of TANESCO based in Meru district, Arusha
city.
Population of the study comprised of a huge number of customers therefore getting all of
them to participate in this study is not possible as a result sampling was inevitable. Sampling/
sample means is a part of the population where the study will take place. (Krishna swami, 1998)
and sample design is a definite plan for obtaining a sample from a given population. It refers to
the technique or the procedure the researcher would adopt in selecting items for the sample
(Kothari; 2005).
3.5 Sampling and Sample Size
3.5.1 Sample Size
The sample size that was used in the study was 60 respondents which included:
30customers, 30 TANESCO staff, geographically respondents was from Meru district of Arusha
city.
3.5.2 Sampling Technique
Determining the proper sampling method is often an arduous task when employing
social scientific research methods. Not only do competing theories of proper sampling for the
notion ofwhat constitutes a good sample, but oftentimes guides offering sampling methods are
indirect or abstract regarding how, exactly, an appropriate sample can be constructed and what
the sample can claim to reflect (Rao, 2000).
Convenience sampling was used to select customers who came to TANESCO’s vending stations
Convenience sampling was used to select customers who came to TANESCO’s vending stations
Convenience sampling was used to select customers who came to TANESCO’s vending stations
to buy electricity. Random purposive sampling method was used to select TANESCO staff
where Respondents was taken from Finance Department as they dealt with revenue of
the company. However each staff was given an equal chance of being selected.
3.6 Type and Sources of Data
Both primary and secondary data was used in this study. Primary data was obtained from the
field whereas secondary data was from statistical reports and database of the TANESCO.
3.6.1 Primary Data
Primary data form first-hand information that the researcher collects for his/her particular study
(Saunders, et al., 2003). Primary data for this study was collected from Meru district where of 30
customers were selected randomly in the area.
3.6.2 Secondary Data
Secondary data are normally data collected earlier for different uses (Saunders, et al., 2003). In
this study, secondary data involved intensive literature review on the similar study undertaken by
different authors. The statistical data and qualitative information, published reports from
TANESCO in Meru district of Arusha will also be used.
3.7 Data Collection
In this study, the researcher will use questionnaires and interviews as a way of data collection.
3.7.1 Questionnaire
A questionnaire is a general term to include all techniques of data in which each person is asked
to respond to the same set of questions in a predetermined order and interview this involve face
to face questions with the respondent and those answer are simple and well under stood to the
researcher. (DeVaus, 2002 as cited by Saunders et al, 2006) Basing on the nature of the study,
the questionnaires were used for both customers and staff members of TANESCO to get
information which was used in the analytical part of the study. This will help to get an in-depth
understanding on the real extent of the effectiveness of prepaid metering system in revenue
collection.
3.7.2 Interview
Is a method of collecting data through oral and verbal communication between the researcher
and the respondent, Both structured and unstructured questions, interview was used because they
are quite flexible, adaptable and can easily allow researcher to see to get more insight on the
topic. It was used to find views of Senior Manager and Manager of TANESCO on the
performance of the prepaid metering system.
3.8 Reliability of Data
It is concerned with consistency of responses with which repeated measures produce the same
result across time and across observers (Saunder et al 2003) three criteria are used in measuring
reliability test retest reliability, Alternative form reliability and internal consistency reliability.
The Cronbach’s alpha coefficient is commonly used to test the manner reliable measure and
instruments were apparent (Katanda, 2004). A 95 % confidence interval was set during the
planning stage in order to achieve accepted levels of data reliability. In addition, the used the
statistical package for social science (SPSS) and Excel to verify reliability of the edited data
using Cronbach’s test.
3.9 Validity
Validity is concerned with whether the findings are really about what they appear to be about.
(Sounder, 2003) During the planning stage an expert was consulted to check the schedule before
actual data collection. All questions were pre tested in the relevant study areas. Modifications
was made before actual data collection for the purpose measuring theoretical meaning
and concepts and consistency of language used to represent concepts thus validity test pre-test
of questionnaire also assisted in detecting irrelevant ambiguous and redundant questions.
3.10 Measurement of Variables
In this study the dependent variable is Revenue collection and the independent variable is the
prepaid metering system.
3.10.1 Measuring Independent Variables
This construct was measured from respondents’ questionnaires where they was asked to
indicate the extent of agreement or disagreement with six statements each concerning the
perceived technologies. How they perceived the use of prepaid meters, the risk of the technology
and cost implications of adopting the technology.
This construct was measured from respondents’ questionnaires where they was asked to indicate
Response was anchored with Likert- scale Independent variables (Perceived risk,
perceived ease of use, cost and perceived usefulness) based on multiple-item constructs, and
was measured through Likert- scale with a scale of 1-strongly Disagree, 2- Disagree, 3-Neutral,
4- Agree and 5- strongly agreed capturing all the desired items of the research variables
3.10.2 Measure of Dependent Variable
The dependent variable (Revenue collection efficiency) was measured by revenue
collection efficiency by method of payment and payment time by the prepaid meter users
3.11 Data Analysis
Data collected from different sources was processed and analyzed for discussion.
Appropriate computer software was used to analyze data. Both Excel and SPSS computer
software were employed to analyze descriptive statistics to see the extent of effectiveness
of the prepaid metering system. Similarly, through the aid of cross tabulations and ordinary
frequency tables and figures, the final outcome showed the true picture of whether the prepaid
metering system was effective in revenue collection.