Correlation Analysis of Independent Variables
Correlation analysis gives the relationship between variables. In this study, Pearson product moment correlation
coefficient (r’s) was used to establish the relationship between the independent variables. The correlation
coefficients are summarized in Table 4.7. The findings also revealed that there was a significant relationship
between the independent variables since all the p-values were less than 0.01, that is p- values 0.000 <0.01. Even
though there was a significant relationship between the independent variables, there was no problem of
multicollinearity among the variables since all the r values were less than 0.8 as suggested by Tabachnick and Fidel
(2007).
Table: Correlation Analysis of Independent Variables
ES RF EC ESS
Pearson Correlation 1 .420** .522** .174*
ES Sig. (2-tailed) .000 .000 .012
N 205 205 205 205
Pearson Correlation .420** 1.297** .385**
RF Sig. (2-tailed) .000 .000 .000
N 205 206 206 205
Pearson Correlation .522** .297** 1 -.128
EC Sig. (2-tailed) .000 .000 .067
N 205 206 206 205
Pearson Correlation .174*.385** -.128 1
ESS Sig. (2-tailed) .012 .000 .067
N 205 205 205 205
**. Correlation is significant at the 0.01 level (2-tailed).
Table: KMO and Bartlett’s test
Variables Measure
Kaiser-Meyer-Olkin Measure of Sampling Adequacy. .815
Social Support Approx. Chi-Square 448.907
Bartlett's Test of Sphericity Df 10
Sig. .000
Kaiser-Meyer-Olkin Measure of Sampling Adequacy. .717
NGOs Performance Approx. Chi-Square 1526.713
Bartlett's Test of Sphericity Df 91
Sig. .000
Regression Analysis for Influence of Social Support
Regression analysis was conducted to establish the association between the social support and performance of NGOs
in Kenya. From the findings, an R- square value of 0.439 was recorded indicating that social support explained 43.9
% of performance of NGOs in Kenya. Model summary table 4.9 shows the findings.
Table: Model summary for Social Support
Model R R Square Adjusted R Square Std. Error of the Estimate Durbin-Watson
2.663a.439 .436 .42455 1.749
a. Model 1 Predictors: (Constant), X4 and X
ANOVA. Employee Social Support
The F-statistics 158.994 presented in table 4.10 indicated that the overall model was significant, that is, the
independent variable, social support was a good joint explanatory for performance of NGOs in Kenya. P- Value was
0.000<0.05 also indicated that the model was fit.
Table : ANOVA. Employee Social Support
Model Sum of Squares Df Mean Square F Sig.
Regression 28.657 1 28.657 158.994 .000b
2 Residual 36.589 203 .180
Total 65.246 204
a. Dependent Variable: Performance of NGOs in Kenya (Y)
b. Model
1 and 2 Predictors: (Constant), X1
Coefficient: Employee Social Support (X1)
From the regression coefficient table, there was a positive and significant relationship between social support and
performance of NGOs in Kenya. The model is given as Y= 1.596+.482X1. The regression coefficient of 0.482
indicated that an increase in employee social support by 1 unit leads to an increase in performance of NGOs in
Kenya by 0.362 units.
Table 4.11: Regression coefficients- Social Support
Model Unstandardized Standardized T Sig. Collinearity Statistics
Coefficients Coefficients
B Std. Error Beta Tolerance VIF
(Constant) 1.596 .162 9.868 .000
1
.482 .038 .663 12.609 .000 1.000 1.00Social Support
a. Dependent Variable: Performance of NGOs in Kenya (Y)
From the analysis, the null hypothesis was rejected indicating that there was a significant relationship between social
support and performance of NGOs in Kenya.
