Nonparametric Bayesian Inference For Survival Data

This article introduces a new Bayesian approach to the analysis of right-censored survival data. The hazard rate of interest is modeled as a product of conditionally independent stochastic processes, corresponding to (1) a baseline hazard function, and (2) a regression function representing the temporal innuence of the covariates. These processes jump at times that form time-homogeneous Poisson processes, and have a pairwise dependency structure for adjacent values. The two processes are assumed to be conditionally independent given their jump times. Features of the posterior distribution, such as the mean covariate eeects and survival probabilities (conditional on the covariate), are evaluated using the Metropolis{Hastings{Green (MHG) algorithm. Some simulation results are presented. We illustrate our methodology by an application to nasopharynx cancer survival data.