Bayesian approach for cure models with a change-point based on covariate threshold: application to breast cancer data

ABSTRACT

In this study, a Bayesian approach was suggested to estimate a change-point according to a covariate threshold when some patients never experienced the event of interest. Gibbs sampler algorithm with latent binary cure indicators was used to simplify the implementation of Markov chain Monte Carlo method. Then, the accuracy of new model was demonstrated by simulation studies to compute the point and interval estimates of parameters. Finally, an effective threshold was suggested in age at surgery time to experience the metastasis when the model was applied for a data set of breast cancer patients.

KEYWORDS:

• Cure rate models
• change-point
• Bayesian analysis
• mixture cure model
• Markov chain Monte Carlo method
• covariates