BART: BAYESIAN ADDITIVE REGRESSION TREES

• 成果类型: Article
• 署名作者: Chipman, Hugh A.; George, Edward I.; McCulloch, Robert E.
• 署名单位: Acadia University; University of Pennsylvania; University of Texas System; University of Texas Austin
• 刊物名称: ANNALS OF APPLIED STATISTICS
• ISSN/ISSBN: 1932-6157
• DOI: 10.1214/09-AOAS285
• 发表日期: 2010
• 页码: 266-298
• 关键词: model; cart

摘要

We develop a Bayesian sum-of-trees model where each tree is constrained by a regularization prior to be a weak learner, and fitting and inference are accomplished via an iterative Bayesian backfitting MCMC algorithm that generates samples from a posterior. Effectively, BART is a nonparametric Bayesian regression approach which uses dimensionally adaptive random basis elements. Motivated by ensemble methods in general, and boosting algorithms in particular, BART is defined by a statistical model: a prior and a likelihood. This approach enables full posterior inference including point and interval estimates of the unknown regression function as well as the marginal effects of potential predictors. By keeping track of predictor inclusion frequencies, BART can also be used for model-free variable selection. BART's many features are illustrated with a bake-off against competing methods on 42 different data sets, with a simulation experiment and on a drug discovery classification problem.