Analysis of Multivariate Failure Time Data Ross L. Prentice and Shanshan Zhao Fred Hutchinson Cancer Research Center and NIEHS
Regression methods that adapt Cox regression to multivariate failure times, on the same or different failure time axes, will be presented. These methods specify Cox –type semiparametric regression models for marginal single and double failure hazard rates, and use estimating functions and empirical process methods, similar to those developed by Danyu Lin, L.J. Wei and colleagues for marginal single failure hazard rates, for hazard ratio parameter and for baseline hazard rate estimation. Sandwich –type variance process estimators are developed for all model parameters, along with a perturbation resampling procedure for complex constructs of modeled parameters. As a byproduct semiparametric estimators of pairwise survivor functions,given covariates that may be evolving in time, are readily obtained from Peano series representations of these survivor functions in terms of marginal single and double failure rates. A large-scale intervention trial application, and simulation study evaluation, will be presented.