Analysis of a composite endpoint with longitudinal and time-to-event data



We propose a new nonparametric test to compare treatment effects using a composite endpoint comprising a longitudinal continuous measurement and multiple time-to-event outcomes. The composite endpoint incorporates the severity of each outcome as measured against the whole cohort in the entire study. This new proposed test is conceptually simple and computationally easy to implement. Unlike many currently available methods, our strategy is very flexible and can be applied to many types of clinical settings including the situation where we have multiple time-to-event outcomes. We apply our method to reanalyze two clinical trials for Scleroderma patients and also use simulation studies to show that the performance of our method is compatible with the results from a popular method proposed by Finkelstein and Schoenfeld (Statist. Med. 1999; 18:1341–1354). Copyright © 2011 John Wiley & Sons, Ltd.