THE TRADITIONAL REGRESSION-MODEL FOR MEASURING TEST BIAS IS INCORRECTAND BIASED AGAINST MINORITIES

For 25 years psychologists have :measured systematic measurement bias in terms of regression lines. According to this traditional approach a test is an unbiased predictor of a criterion for all subgroups if all subgroups have identical Y' regression lines (i.e., identical slopes and identical Y' intercepts). This paper shows that the traditional mo del is fundamentally incorrect and identical Y' regression lines are n ot expected to occur with an unbiased test in a testing situation in w hich one group score lower than another group on both the test and cri terion. This is the case even if the test is perfectly reliable. The t raditional model for measuring bias actually results in a consistent e rror or bias against groups which score lower than average on both the test and criterion. In practice this bias operates against minority g roups. Tests now thought to be unbiased or even biased in favor of min ority groups may in fact be biased against minority groups. A new mode l of test bias, which is based solely on measurement principles, is br iefly introduced. In this model unbiased tests produce groups with ide ntical test-criterion common-factor axes having a slope of S-YC/S-XC a nd with each axis intersecting the group centroids.