Large Sample Estimates of the Reliability of Simple, Residualized, and Base-Free Gain Scores

Abstract

Because of limitations in simple gain scores, psychometrists have proposed alternate methods for measuring change, two of which are the residualized difference and the base-free change. The purpose of the present investigation was to provide large sample empirical estimates of the reliability of these change measures, and to check theoretical predictions derived from inequalities involving all three change measures. Although the theoretical predictions were supported, all of the gain score reliabilities were rather low. In order for gain scores to be reliable it is necessary for the intervention between the two testing occasions to be relatively potent and for the instrumentation to be specially designed to be sensitive enough to detect changes attributable to the intervention.