Two problems in the investigation of predictive bias in tests, the effect of unreliability of the predictors, and the effect of excluding a predictor from the regression equation on which there are preexisting group differences, are discussed. (Author)

Models proposed by Cleary, Thorndike, Cole, Linn, Einhorn and Bass, Darlington, and Gross and Su for analyzing bias in the use of tests in a selection strategy are surveyed. Several additional models are also introduced. The purpose is to describe, compare, contrast, and evaluate these models while extracting such useful ideas as may be found in…

Two of the groups whose relationship represents one of the most critical social problem areas are also the groups on whom there is a large amount of data. These are American Negroes and American Caucasians, or in today's terminology, blacks and whites. Some data relevant to the design of programs of social action suggest the following: The mean…

Three alternative strategies for college selection, their associated cost and benefits are described in this study. These include a strict meritocratic procedure, a minority quota procedure and a disadvantaged quota procedure. The strict meritocratic procedure was operationalized in terms of predicted probability of success; the minority quota…

Samples of Anglo, Black, Mexican-American, and Papago Indian students (N=260 per group) were administered the Metropolitan Achievement Test and the Wechsler Intelligence Scale for Children-Revised (WISC-R). Various concepts of cultural fairness were identified from the literature and then used to design analyses of these data. Regression equations…