Bayesian Estimation and Variable Selection of Accelerate Failure Time Models

This paper mainly proposes Bayesian methods to analyze the accelerated failure time models. In this model, the distribution of the error terms is unknown and approximated with a P\'olya tree distribution. This paper employs the Bayesian Lasso and Markov chain Monte Carlo methods for parameter estimation and variable selection. Simulation studies demonstrate that the proposed methods can identify the important factors and provide accurate estimates. Finally, the proposed model is applied to identify the risk factors of survival times of the Type II diabetic patients.