Statistical Approaches for Multiple Event-Time Outcomes
*Ionut Bebu, The George Washington University  John Lachin, The George Washington University 


Composite outcomes are common in clinical trials, especially for multiple time-to-event outcomes (endpoints). The standard approach that uses time to the first outcome has important limitations. Two alternative approaches to compare treatment versus control will be described. The first approach is an application of the Wei-Lachin multivariate one-directional test to multiple event-time outcomes. The test statistic is based on the (un)weighted mean of the treatment group coefficients from individual Cox proportional hazards models fit to the outcomes, where the covariance of the set of coefficients is obtained from a partitioning of the information sandwich estimate. The second approach is a win ratio/difference analysis based on prioritized outcomes. Tests of significance and confidence intervals are obtained using the large sample distribution of certain multivariate multi-sample U-statistics. The methods are illustrated with time-to-event outcomes data from a clinical trial.