The problem of testing for differences between two groups with respect to multiple competingrisk time-to-event endpoints is considered A class of two-sample test is proposed for comparing thesubdistribution of a particular type of failures. The test is based on comparing the weighted averageof subdistribution functions without making any assumption on the nature of dependence among therisks. The weight function has been chosen so that the test is distribution-free in the sense thatasymptotically valid test can be performed without assumption regarding the underlying survival andcensoring distribution. Both theoretical result and simulation evidence show that the proposedmethod attains the nominal level. We also apply the test to real data.
Copyrights © 2005