Variable selection priors for survival models with censored data

M. E. Castellanos Nueda, G. García-donato Layrón, S. Cabras

We consider the variable selection problem when the response is subject to censoring. A main particularity of this context is that information content of sampled units varies depending on the censoring times. We approach the problem from an objective Bayesian perspective where the choice of prior distributions is a delicate issue given the well-known sensitivity of Bayes factors to these prior inputs. In this paper, we develop specific methodology based on a generalization of the conventional priors (also called hyper-g priors) explicitly addressing the particularities of survival problems arguing that it behaves comparatively better than standard approaches on the basis of arguments specific to variable selection problems (like e.g. predictive matching). For illustrative purposes, we apply the methodology on a classic transplant dataset and to a recent large epidemiological study about breast cancer survival rates in Castellón, a province of Spain.

Keywords: Bayes Factors, Conventional Priors, Model Selection

GT8-2 Bayesian Inference
September 4, 2019  12:00 PM
I2L7. Georgina Blanes building

R. Sillero Denamiel, J. M. Marín, P. Ramirez Cobo, F. Ruggeri, M. Wiper

P. Barbillon, A. Forte Deltell, R. Paulo

R. Morales Arsenal, M. Á. Gómez Villegas