Conferencias
Jorge Alberto Achcar
Departamento de Medicina Social, FMRP, Universidade de São Paulo, Ribeirão Preto, SP, Brazil
We present estimates for the parameters included in lifetime parametric distributions in presence of covariates and cure fraction, applied to analyze survival data when some individuals may never experience the event of interest and two lifetimes are associated with each unit. As a special case, we assume the Block and Basu bivariate exponential distribution. We further assume a general parametrical modeling based on some standard copula functions to capture the dependence among the lifetimes, where any univariate lifetime distribution could be assumed as marginal distributions. A Bayesian procedure is used to get point and confidence intervals for the unknown parameters. Posterior summaries of interest are obtained using standard Markov Chain Monte Carlo methods in rjags package for R software and also using the OpenBugs software. An illustration of the proposed methodology is given considering lifetime medical data.
