COMPARATIVE-EVALUATION OF 2 MODELS FOR ESTIMATING SAMPLE SIZES FOR TESTS ON TRENDS ACROSS REPEATED MEASUREMENTS

Two equations for calculating sample sizes that are required for power in tasting differences in rates of change in repeated measurement des igns have been presented by different authors. One equation provides s upport for the conclusion that increased frequency of measurements acr oss a treatment period of fixed duration enhances power of the tests. The other equation supports the counterintuitive conclusion that incre ased frequency of measurements actually tends to decrease power in the presence of realistic serial dependencies in the data. Monte Carlo me thods confirm that the equation providing support for the latter concl usion is accurate, whereas the alternative equation tends to underesti mate sample sizes required for power in testing differences in slopes of regression lines fitted to changes in the repeated measurements acr oss time when symmetry is absent from the covariance structure. (C) El sevier Science Inc. 1998.