Using Empirical Bayes Techniques in the Law School Validity Studies

Abstract The law school validity studies are primarily concerned with the prediction of first-year average in law school from Law School Aptitude Test score and undergraduate grade point average. Traditionally, a separate admitting equation is estimated in each law school by the method of least squares based on data from students who attended the law school in recent years. These least squares equations can fluctuate rather wildly from year to year. This study employs empirical Bayes techniques to obtain admitting equations that are better than the least squares admitting equations in two ways: for each law school, the empirical Bayes admitting equations are more stable in time than the least squares admitting equations; and the empirical Bayes admitting equations predict student performance more accurately than the least squares admitting equations.