THE MEASUREMENT AND COST OF REMOVING UNEXPLAINED GENDER DIFFERENCES IN FACULTY SALARIES

In the assessment of damages for sex discrimination suits, most of the debate between plaintiffs and defendants concerns the type and number of variables to include in a single equation model of the salary determination process. Even within a restrictive single equation framework there are alternative methods available for calculating damages, and these different methods can result in substantially different costs when based on semilogarithmic earnings equations. Here we consider both single and multiple equation models in damage calculations. We provide thirty-six different damage calculations and show that, at least for data from the University of Minnesota, the cost of equalization depends greatly on the combinations of models, methods, and estimators.