APPLICATIONS OF A MIXTURE SURVIVAL MODEL WITH COVARIATES TO THE ANALYSIS OF A DEPRESSION PREVENTION TRIAL

This paper presents a case study of model selection for survival analy sis data. We use an approximate Bayesian method for model selection ba sed on assessing the posterior probability of competing models given t he data. We introduce the Schwarz criteria, an approximation to the lo garithm of the Bayes factor, to provide an indication of evidence in f avour of one model compared to another. Specifically,in the context of a depression prevention clinical trial we evaluate the efficacy of tr eatment in preventing or delaying the time to recurrence of depression , and evaluate how differences in the survival distributions between t he two treatment groups depend on explanatory variables of interest. T his investigation is based on a mixture survival model that explicitly incorporates the possibility of a surviving fraction.