extremely large for most of the models (e.g., 26.89, 40.39, 17.96, 38.77; the smallest F-statistic was 12.43, an F-ratio of 16/162 degrees of freedom, where the tabled value of F(6, 162, .01) is approximately 6.81). This indicates very strong results. Also, the R-squared values were relatively high for all of the models, particularly considering the complexity of the salary determination studies. process and the R-squared values obtained in other similar 31/ The R-squared value indicates the amount of variation of the dependent variable explained by the regression equation. For example, an R-squared of .659 means that 65.9 percent of the variation in salary is explained by the regression equation; 34.1 percent of the variation remains unexplained. The table on the following page gives the R-squared values for the twelve models developed in this study. In addition to testing the statistical significance of the overall regression fit as in the F-statistics discussed above, t-tests were used to evaluate the statistical significance of the individual regression coefficients in 31/ For example, in the research of George F. Travers, Jr. of the Office of Federal Contract Compliance; and others. each model. Those coefficients not found to be significantly different from zero in a statistical sense were eliminated from the regression equation. The table of significant salary determiners, which follows on page 90, shows which coefficients were significant and which ones were not for each of the twelve models. After eliminating those variables whose regression coefficients are not statistically significant, we can consider the salary models for some of the racial-sexual groups. They are as follows: For white males: S = $3042 X 1n service + $2414 X DPMS/SOL S = $2260 X 1n service + $2929 X degree $2328 X Dallas/KC/Boston + K For black males: S = $434 X age + $914 X 1n service + $3160 X degree + $7365 X adv degree + $1676 X Manpower + K Statistically Significant Explanatory Factors Explanatory | Alpha-level of Significance, by Regression Model * black black all sional male female male female white * A dash indicates that the variable was not used in that particular regression where: (1) (2) In service is the natural logarithm of years degree, adv degree, female, Manpower, DPMS/SOL, (3) K is the appropriate constant for each model 32/. These salary models show striking differences in the magnitude of the coefficient for years of government service. They range from $3402 for white males to $914 for black males. This result is consistent with our findings in Section B-1 above that show length of government service to be an important salary determiner for white male 32/ The constant term was not statistically significant in any of the regression models. In any case, it would have to be recalculated after elimination of the variables whose regression coefficients were not statistically significant. The K in these equations represents the constant term after recomputation. The computation can be accomplished by taking the product of the regression coefficient and the expected value (mean) for all variables eliminated from the equation; these products are then summed and added to the constant term. |