Relationship Assessment on Disbursement of Loan on Agricultural Credit Guarantee Scheme Fund

Abstract

This research work was aimed at carrying out Linear relationship between total loan granted; Loan granted to individual, cooperative, company from 2003-2022. Secondary data was obtained from the Agriculture Credit Guarantee Scheme Funds. The statistical package used is SPSS and Rstudio. The result shows that out of the independent variables, individual and cooperative contributed meaningfully to the fitted model. The test for the predictive power revealed that the model has a high predictive power and it means that 79.2% of the total is explained by the regression equation, this indicates that the prediction made on total is reliable at 79.2%. Generally the model is reliable for predictions since there is a variable that contribute to the fitted model using individual test. The test for the existence of heteroscedasticity using the spearman rank correlation shows that the rank correlation coefficient between the absolute value of the error term e­_i and each of the explanatory variables (individual, cooperative and company) are low which indicates the presence of homoscedasticity. Test of autocorrelation with Durbin Watson statistic of 2.271 (approximately equal to 2) and autocorrelation of 0.1355~0 which shows that autocorrelation does not exist. The test for linearity reveals that there is no linear relationship between the dependent variable and the independent variables which indicate that the linear assumption is violated. The test for normality shows the dot plot close to the expected cumulative line which is an indication that the residuals are normally distributed that is the normality of the residual assumption was not violated in the course of fitting regression model.