A statistical study on the determinants of wage differences in Uganda
Abstract
The study centered at finding the determinants of wage differences. Wage difference is simply the difference in the payment among workers with difference in education level, total level of work experience, age, sex etc. under the same organization or company with the same qualities but under different organizations. Difference in wages among employees has led to increased income inequality in Uganda and this later reflected on the GDP of the economy. The main objective of this study was to assess the determinants of wage differences in Uganda. Therefore, it aimed at finding out whether age, education level, region, number of hours worked, marital status have a significant relationship with the wage differences. It used secondary data and was obtained from the Uganda Bureau of Statistics. The analysis was done using frequency distribution, summary statistics, one way analysis of variance, and correlation matrix and multi linear regression. In the descriptive analysis, majority of the workers are male (81.8%). Majority of workers access transport by their own means (78.9%). Slightly more than a half of the workers attained primary level of education (56.8%) and lastly, slightly lower than a half of the workers have a total level of experience of 4 years and above (48.6%). In the bi -variate analysis ,There is no significant difference in the performance between group means for means of transport (F-value =1.72, P-value=0.5872).There is a significant difference in the performance between group means of level of education (F-value =11.81, Pvalue=0.0000).There is a significant difference in the performance between group means of region (F-value =34.84, P-value=0.0000).There is a significant difference in the performance between groups mean of sex (F-value =22.34, P-value=0.0000). In the multivariate analysis, The R-squared was found to be 0.4277 and the adjusted R-squared was found to be 0.4250 and this implies that the variations in explanatory variables in the model explain 42.8% of the variations in wages. This implies that the model is a good fit and thus the variations in the explanatory variables explain the variations in the wages at 5% level of significance.