A Generalized Bayesian Ensemble Survival Tree (GBEST) model

This paper proposes a new class of predictive models for survival analysis called Generalized Bayesian Ensemble Survival Tree (GBEST). It is well known that survival analysis poses many different challenges, in particular when applied to small data or data with critical levels of censorship. Our contribution is the proposal of an ensemble approach that uses proper Bayesian bootstrap and Beta Stacy bootstrap methods to improve the outcome of survival application with a special focus on small datasets. More precisely, a novel approach to integrate Beta Stacy bootstrap in bagging tree models for right-censored data is proposed. Empirical evidence achieved on simulated and real data demonstrates the superior performance of our approach in terms of predictive performance and results stability compared with classical survival models available in the literature. In terms of methodology, our novel contribution considers the adaptation of recent Bayesian ensemble approaches to survival data, providing a new model called GBEST. The R code for GBEST is available in a public GitHub repository.