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
$4021 X Atlanta - $3358 X San Fran/Chic
- $2395 X Dallas/KC/Boston
+ K

For white females:

$3696 X New York

S = $2260 X 1n service + $2929 X degree

+ $4154 X adv degree - $2188 X Atlanta

$434 X age + $914 X 1n service + $3160 X degree + $7365 X adv degree + $1676 X Manpower + K

*

A dash indicates that the variable was not used in that particular regression
model, and a blank space indicates that the coefficient was not statistically
significant at either the 1 percent or 5 percent alpha-levels.

where:

(1) ln service is the natural logarithm of years

cf government service;

(2) degree, adv degree, female, Manpower, DPMS/SOL, Atlanta, San Fran/Chicago, Dallas/KC/Boston,

(3)

and New York are dummy variables; if an em

ployee is a member of the group represented

by the dummy variable, the variable assumes
the value of 1; otherwise, its value is Ø; and
K is the appropriate constant for each model32/.

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.

professionals, who progress steadily from the entry level grades to at least grades 13 and 14 and who have enjoyed such predictable progression for a number of years.

White males, then, with long government service tend to be in the higher grades. For black male professionals, however, the average length of government service at each grade level was found to be relatively constant across the grades. Thus, length of government service is a much less significant indicator of salary for black males than for white males. Black males have not benefited from predictable promotion patterns as have white males. And this is what is shown by the large differences among the coefficients for government service of the various salary

models.

beta coefficients.

33/

Such differences are also revealed by a comparison of For each variable of a regression model, its beta coefficient is the product of its regression coefficient and its variance, divided by the variance of the dependent variable. The beta coefficient represents

33/Note that the use of beta coefficients is not

a different way of comparing regression coefficients as much as it is a more meaningful way. It is certainly not independent from other comparisons.

a standardization of the coefficient-variance products by

the variance of the dependent variable, permitting a valid comparison of these products. One would expect independent variables with large variances and large regression coefficients to have large effects on the value of the dependent variable. Thus, we can use the beta coefficients as an indication of the relative importance of individual independent variables in determining salary. The table on

page 94 ranks the beta coefficients by magnitude by regression model for all of the models. Comparing the ranks for the government service variable, we again see the important differences existing among salary models. For example, the service beta coefficient for white males ranked first among beta coefficients in the white male model, while the service beta coefficient for black males ranked sixth in the black male model. Thus, the great

difference between black and white males in the relative

importance of government service as a salary determiner is illustrated again.

g. Racial and sexual implications of the results.

Referring to the table (page 90 ) listing the sta

tistically significant explanatory factors for each salary