C. Armero Cervera, S. Cabras, M. E. Castellanos Nueda, S. Perra, A. Quirós Carretero, M. J. Oruezabal Moreno, J. Sánchez Rubio Ferrández
Bayesian reasoning, survival analysis and multi-state models are used to assess survival times for Stage IV non-small cells lung cancer (NSCLC) patients and the evolution of the disease over time. Bayesian estimation is done under the Jeffreys' prior for the Weibull regression survival model leading to an automatic inferential procedure. Uncertainty about the parameters of the model is expressed in terms of its posterior distribution, approximated via Markov Chain Monte Carlo methods, and it has been propagated to the hazard rate functions of the times between transitions. We can thus obtain the posterior distribution for the transition probabilities, given the time and the covariates, which offers a complete description of the dynamics of the system. Data for the study come from the Infanta Cristina Hospital of Madrid, Spain, and consist of survival times for stage IV NSCLC patients and measures of several covariates that may be related to the disease.
Palabras clave: Bayesian information criterion, survival analysis, transition probabilities
Programado
MD1 Métodos bayesianos 2
17 de abril de 2012 15:30
Salón Madrid
