Combined evidence from multiple outcomes in a clinical trial

Clinical investigators are encouraged to apply recently developed statistic al methodology. For each patient in a trial, favorable and unfavorable resu lts from multiple outcomes may be summarized in a suitable summary measure. This summary measure may be used in a two-sample t-test to decide which tr eatment is best. An example illustrates how the evidence from the main outc ome criteria may be combined. The required study size depends on the mean t reatment effect on the outcomes in the summary measure. When separate outco mes are considered, there is a multiple comparisons problem, for which Hoch berg offered a simple solution. Evaluation of a single-summary measure may require a larger or a smaller study size than evaluation of separate outcom es, depending on whether treatment effects are about the same or very diffe rent. (C) 2000 Elsevier Science Inc. All rights reserved.