Objective Bayesian analysis of Weibull mixture cure model

Abstract

In this article, we conduct objective Bayesian analysis for the mixture cure model based on the Weibull distribution with right-censored data. By introducing latent variables, the complete likelihood function of the model is given and from that the Fisher information matrix is obtained by approximation. We obtain the maximum likelihood estimates by EM algorithm, and derive objective priors including Jeffreys prior, reference priors, and matching probability priors to carry out Bayesian estimation. A simulation study and a real data analysis illustrate the methods proposed in this article, and show that the objective Bayesian method gives better performance under small sample sizes compared to maximum likelihood method.