Regression Table Interpretation

The results of the analysis on the effect of the process on professional commitment are shown in Table (4.11). According to the results from multiple linear regression analysis, it is found that the professional commitment of women ICT professionals is positively related to compensation and training and development provided by their companies.

As shown in Table (4.11), the R square is 0.609. Thus, the linear regression model in this case can explain 60.9% of the relationship between independent variables (Compensation and Training and Development) and the dependent variable (professional commitment). According to significance values, it is found that there is a positive relationship between compensation training development and professional commitment. All VIFs are less than 10 which means there are no problems of multicollinearity among independent variables. According to the analysis, it is found that compensation is strongly associated significant level of one percent. It is said that compensation makes women have individual and professional affective attachments and bind with their companies. The training and development are slightly less associated with a two-star significance level to their individual professional commitment and job satisfaction in their companies.

[As shown in Table, the value of the adjusted R square is (  ), this model can explain ( )% of the variation of (dependent variable), which is predicted by the measures of (independent variable). Since the F-value, the overall significance of the model is highly significant at 1% level, the model is said to be valid. From multiple linear regression analysis, the coefficient of ( sig ဖြစ်တဲ့ independent variable) is significant at ( sig %) percent level. A unit increase in (sig ဖြစ်တဲ့ independent variable) results in ( ) units increase in (Dependent variable). The Durbin-Watson value is close to 2 ( ). Therefore, it indicates that there is no autocorrelation in the sample. Concerning potential problems relating to multi-collinearity, variance inflation factors (VIF) were used to provide information on the extent to which non-orthogonality among independent variables inflates standard errors. All VIF values are less than 10, meaning that the independent variables are not correlated with each other. Therefore, there are no substantial multi-collinearity problems encountered in this study.]