Matthew Pratola, Associate Professor, Department of Statistics, The Ohio State University
Title: Bayesian Regression Tree Models: Origins, Applications, and the Future
Abstract:
BCART (Bayesian Classification and Regression Trees) and BART (Bayesian Additive Regression Trees) are popular Bayesian regression tree models widely used in modern regression problems. Their popularity stems from the ability to model complex responses depending on high-dimensional inputs while simultaneously being able to quantify uncertainties. This ability to quantify uncertainties is key, as it allows researchers to perform appropriate inferential analyses in settings that have generally been too difficult to handle using the Bayesian approach. In this talk, we first introduce the Bayesian regression tree modeling framework and explore the tree-prior and its implications. Then, motivated by the uncertainty quantification capabilities of the model, we explore some of our recent methodological developments inspired by applications in physics, climate and engineering. We conclude with an outlook on future directions, particularly in verifiable statistical modeling.