Multiple regression analysis was performed on

Multiple regression analysis was performed on profitability of deposit taking SACCOs as the
dependent variable whereas Loan performance management, fixed assets management, financial
investments management and accounts receivable management were the independent variables in
the model. Analysis of variance (ANOVA) was also be used to test the significance of the model
in explaining the relationship between variables.
The formulated research hypotheses was tested using regression analysis at 5% significance
level. The following model was adopted to explain joint effect of predictor variables on the
dependent variable
Y= β
0
+ β
1
X
1
+ β
2
X
2
+ β
3
X
3
+ β
4
X
4
+ ε; Where;
Where
Y Profitability of deposit taking SACCOs measured as Net income divided by Total assets
β
0
Y- intercept
X
1
Loan performance management
X
2
Fixed assets management
29

X
3
Financial investments management
X
4
Accounts receivables management
β
1
, β
2
, β
3
& β
4
- Beta coefficients for the independent variables respectively ε
Error term normally assumed to be randomly distributed
3.8 Ethical Consideration
According to MulaG and Sarkar, S.C, (2013), ethics involves the study of right and wrong
conduct. The researcher was very careful to avoid physical and psychological harm to the
respondent in the process of data collection by not asking irrelevant or embarrassing questions
(Mugenda and Mugenda, (2008). The researcher gave assurance to the respondents that the
information collected would be kept confidential. The researcher informed the respondents that
the purpose of the study was purely academic. The researcher exhibited moral character of an
academician in the process of data collection period to get co-operation of respondents. The
researcher encouraged a free corruption exercise by using mature people in data collection. This
helped to keep the principle of confidentiality, avoidance of deception and anonymity, Sommer
and Sommer, (2009).
CHAPTER FOUR
DATA ANALYSIS, INTERPRETATION AND PRESENTATION
4.1 Introduction
This chapter presents the data analysis results, their presentation and interpretation. The chapter
begins with the demographic characteristics of the respondents such as gender, age, academic
qualifications, and years worked. Descriptive statistics are also presented. The results from the
correlations and the regression analysis are also presented.
30

4.2 Response Rate
According to Babbie (1990), a response rate of 50% is adequate, 60% is good and 70% is very
good for analysis and reporting from manual surveys. Table 4.1 below shows the response rate.
Out of 110 questionnaires administered to the respondents, 82 were fully completed and returned
making the response rate be 74.5%. This was above the expected response rate of 50-70% hence
making it sufficient to perform data analysis of the research objectives.