HIT-RATE BIAS IN MENTAL TESTING

New results are given concerning a form of test bias which, in the pas t, with few exceptions (esp. Cole, 1973; Hartigan & Wigdor, 1989), see ms to have been largely ignored. We call it ''hit-rate bias'' because it is defined as the discrepancy between the hit-rates (= probability that a qualified testee passes the test) in a low- and a high-scoring group. Typically, it favors the high-scoring group. In contrast to Col e (1973), our focus is on binary criteria, such as college graduation. In the first, theoretical part, we present a (Hit-Rate Bounds) Theore m which underscores that raising predictor standards is not equivalent to raising criterion standards, as some believe. Instead, it typicall y increases hit-rate bias. We then derive and tabulate a simple approx imation for estimating hit-rates as a function of validity, base-rate, and admission quota. In the empirical portion of the paper, we evalua te the extent of hit-rate bias in practice by re-analyzing a number of data sets involving the SAT, the ACT, and the GATE. Finally, we discu ss how the addition of test scores to high school record affects hit-r ate bias in predicting college graduation. We find it increases the bi as.