A0397
Title: Bayesian regression tree ensembles for survival analysis
Authors: Richard Hahn - Arizona State University (United States) [presenting]
Abstract: Aspects of time-to-event data that make it challenging for non-parametric covariate adjustments are reviewed. Recent work using tree-ensembles for survival analysis is based on a covariate-dependent version of the traditional Kaplan-Meier estimator, but is computationally impractical in many applied settings. We derive a continuous-analogue of the Kaplan-Meier estimator and describe how it can be used to do survival analysis with generic machine learning methods for conditional density estimation.
