Marginal proportional hazards models for multiple event-time data

The Wei et al. (1989) semiparametric approach to the analysis of multiple e vent-time data assumes that each event time is related to covariates throug h a proportional hazards model with a completely unspecified baseline hazar d function, but does not impose any constraint on the joint distribution of different event times. As a result of the order restriction, it is not cle ar whether or not event times can simultaneously satisfy their respective m arginal proportional hazards assumption, while having continuous joint dist ribution. This leads to inability to conduct simulation studies. We resolve this issue by constructing parametric models for multiple event times with proper joint density functions and marginal proportional hazards. Simulati on studies are reported that compare efficiencies of the method of Wei et a l. (1989) and of the maximum likelihood approach.