A flexible model for survival data with a cure rate: a Bayesian approach

Abstract

In this paper we deal with a Bayesian analysis for right-censored survival data suitable for populations with a cure rate. We consider a cure rate model based on the negative binomial distribution, encompassing as a special case the promotion time cure model. Bayesian analysis is based on Markov chain Monte Carlo (MCMC) methods. We also present some discussion on model selection and an illustration with a real data�set.survival analysis, cure rate models, long-term survival models, negative binomial distribution, Bayesian analysis, piecewise exponential distribution, Weibull distribution,

A general long-term aging model with different underlying activation mechanisms: Modeling, Bayesian estimation, and case influence diagnostics

“…For instance we cite Chen et al [1999] and Cancho et al [2011b]. However, the Bayesian approach to LRC model under a variety of activation mechanisms has never been considered.…”

“…Following the proposition of comprehensive cure rate models [Yakovlev and Tsodikov, 1996], , [Chen et al, 2002], [Chen et al, 1999], [Tsodikov et al, 2003], [Tournoud and Ecochard, 2007], [de Castro et al, 2009], [Ortega et al, 2009], [de Castro et al, 2010], [Cancho et al, 2011b] and [Kim et al, 2011] include in their formulation the possibility of having a cured rate in the population, and assume the occurrence of the event of interest might be a result of many competing causes [Gordon, 1990], but both number of causes and survival times associated with each cause [Cox and Oakes, 1984] being unknown, which leads to the so-called latent competing causes [Louzada-Neto, 1999], which are assumed to follows a discrete distribution such as the Poisson, the negative binomial, the geometric, the COM-Poisson, the power series, amongst others.…”

The destructive negative binomial cure rate model with a latent activation scheme

“…(2007), here we introduce a destructive (compound) negative binomial (DNB) cure rate model which demonstrates greater flexibility than the proposition of Cancho et al (2011) by considering a stochastic framework for the ordered sequence of latent factors leading to disease manifestation. Our parametrization allows us to model both under- and over-dispersion, commonly encountered in discrete data.…”

Negative Binomial Kumaraswamy-G Cure Rate Regression Model

“…More recently, proposed a unified theory of long duration, considering different competitive causes. In this context, most long-term models make use of this proposal, among which are (Sy and Taylor 2000;Castro et al 2009;Cancho et al 2011;Gu et al 2011), besides (Ibrahim et al 2005;Cooner et al 2007;Ortega et al 2008Ortega et al , 2009Cancho et al 2009).…”