Online Program Home
My Program

Abstract Details

Activity Number: 102
Type: Invited
Date/Time: Monday, August 1, 2016 : 8:30 AM to 10:20 AM
Sponsor: Section on Bayesian Statistical Science
Abstract #318022 View Presentation
Title: Dispersion Modeling with an Ensemble of Trees
Author(s): Hugh Chipman* and Matthew Pratola and Robert McCulloch and Edward I. George
Companies: Acadia University and The Ohio State University and The University of Chicago and The Wharton School
Keywords: Supervised learning ; BART ; ensemble ; Bayesian

Bayesian additive regression trees (BART) is a flexible and scalable supervised learning model that offers accurate assessment of uncertainty via credible intervals. A strong assumption made by the BART model is that errors are iid. When error variance is nonconstant, point predictions from BART can still be accurate. However, credible intervals are unlikely to remain accurate or useful. Moreover, in many applied problems, understanding the relationship between the variance and predictors can be just as important as that of the mean model. We develop a novel heteroscedastic BART model to alleviate these concerns. Our approach is entirely non-parametric and does not rely on an a priori basis for the variance model. This is achieved through the introduction of Bayesian Multiplicative Trees, which model the variance component of BART as a function of the predictors. We implement the approach and demonstrate it in several examples.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2016 program

Copyright © American Statistical Association