In this study, I investigated 2 procedures intended to create test-taker groups of equal ability by poststratifying on a composite variable created from demographic information. In one procedure, the stratifying variable was the composite variable that best predicted the test score. In the other procedure, the stratifying variable was the composite that best indicated group membership (i.e., the propensity score). Applied to 2 groups taking the same test at different administrations, the composite that best predicted the test score reduced the ability difference by about two thirds; the composite that best indicated group membership reduced the ability difference by about half. Prescreening the predictor variables did not improve the performance of either procedure.