MnSCU – System Report

2002 Salary Equity Analysis

March, 2003

Prepared by:

Thomas McMullen

Senior Consultant

Hay Group

Eric Jacobs

Consultant

Hay Group

Malcolm M. Dow

Professor Emeritus

Northwestern University

Table of Contents

I. Executive Summary.................................................................................................... 1

II. Faculty Salary Equity Analysis................................................................................... 2

A. Controlling Salary For Structural Factors: Multiple Regression Analysis................. 2

B. Individual-level Salary Differences: Regression Residuals..................................... 11

C. Summary................................................................................................................... 11

I. Executive Summary

Faculty Salary Analyses Highlights

This statistical analysis of the System faculty salary data used the Multiple Regression model to predict salaries based on a number of factors known to affect pay. Variables coding for campus location were included in the analyses. No faculty performance measures were included.

A set of location dummy (0,1) variables were included in one of the regression analysis to assess overall differences across campuses. This regression analysis revealed a spread of approximately 5.5% (-3.3% to +2.2%) in average salaries across campuses, after controlling for all of the other variables in the model.

The regression analysis using years in current rank and other time-related variables, plus the squares of these variables, showed no evidence of salary compression for faculty with many years in rank. However, the appointment status variables suggest that hiring faculty at the higher academic ranks but without tenure, and at higher average annual salaries than comparable tenured faculty, may lead to salary compression problems in the future.

At the individual level, shortfalls between actual salary and salary predicted by the Total Population regression model (without location), as indicated by standardized residuals of less than -1.00, were noted for 278 faculty across all campuses.

II. Faculty Salary Equity Analysis

A. Controlling Salary for Structural Factors: Multiple Regression Analysis

1. Total Population Salary Analysis – with and without location

Table 1 reports the estimated regression equation and auxiliary statistics for the Total Population Analysis (N=2,370). In this model, the dependent variable is 2002 Annual Salary, and the predictor variables are all of the structural variables.

The first column of Table 1 shows the labels of each of the variables entered into the regression model. The first term (constant) can be ignored. Each of the other terms in the first column corresponds to a “structural” variable. The second column in Table 5 shows the “unstandardized coefficient” B associated with each variable, which indicates the average amount by which each faculty member’s salary increases (or decreases) for a one unit change in the corresponding variable, all of the other variables in the equation being held constant. In the case of a dummy variable, the one unit change is from the omitted reference category (coded as 0) to the corresponding category (coded as 1). So, for example, the coefficient for Associate Professor in the second column indicates that an individual moving from the “Professor” category (coded as 0) to the “Associate Professor” category (coded as 1) would be expected to have a decrease in annual salary of $3,490, all other variables in the regression model being held constant. That is, this figure is simply the difference in average salaries between the two ranks controlling for all other variables in the model. For continuous variables, such as Years since Highest Degree, the corresponding unstandardized coefficient ($87) indicates how much each additional unit (here, a year) is worth, on average.

Table 1. Total Population Model with Discipline, no Location.


	Unstandardized		Standardized	t	Sig.	Collinearity
	B	Std. Error	Beta	t	Sig.	Tolerance	VIF
(Constant)	57060	428		133.403	0.000

ACCTG	11110	716	0.129	15.520	0.000	0.743	1.346
ALHEL	1477	894	0.013	1.652	0.099	0.846	1.182
ARTFI	795	758	0.010	1.049	0.294	0.595	1.679
AVIAT	2928	1448	0.015	2.022	0.043	0.927	1.079
BIOLO	1007	574	0.016	1.756	0.079	0.645	1.549
BUSLW	7339	1445	0.039	5.080	0.000	0.847	1.180
CHEMS	-15	719	0.000	-0.021	0.983	0.765	1.308
CISCS	10744	557	0.175	19.284	0.000	0.622	1.609
COUED	1477	918	0.012	1.609	0.108	0.861	1.161
COUNS	594	854	0.005	0.696	0.487	0.841	1.189
CRMJS	1790	985	0.014	1.817	0.069	0.876	1.141
CULTR	1758	722	0.020	2.435	0.015	0.775	1.291
ECONO	5325	735	0.059	7.245	0.000	0.778	1.285
EDBUS	4146	2003	0.015	2.070	0.039	0.967	1.034
EDCAD	2753	937	0.023	2.937	0.003	0.857	1.167
EDCGN	1223	499	0.024	2.448	0.014	0.517	1.933
EDCSP	1324	844	0.012	1.568	0.117	0.835	1.198
ENGIN	11895	849	0.110	14.009	0.000	0.825	1.212
(ENGLISH)
FINAN	13746	880	0.121	15.626	0.000	0.845	1.184
GEOGR	453	774	0.005	0.586	0.558	0.802	1.246
HISTY	-713	729	-0.008	-0.978	0.328	0.775	1.290
HOMEC	-725	2007	-0.003	-0.361	0.718	0.963	1.038
LANGS	-744	745	-0.008	-1.000	0.318	0.791	1.264
LIBRY	1104	611	0.017	1.809	0.071	0.606	1.649
MARKT	13055	819	0.126	15.931	0.000	0.813	1.229
MATHM	1553	520	0.028	2.985	0.003	0.578	1.730
MEDIA	1345	757	0.014	1.776	0.076	0.782	1.279
MNGMT	11974	665	0.150	17.994	0.000	0.736	1.359
MUSIC	-542	616	-0.008	-0.880	0.379	0.702	1.424
NURSE	3579	613	0.053	5.839	0.000	0.615	1.626
PHILO	281	799	0.003	0.351	0.725	0.812	1.232
PHYED	532	543	0.011	0.979	0.328	0.397	2.522
PHYSC	1598	688	0.019	2.322