mBART: Multidimensional Monotone BART
Bayesian Analysis · 01.06.2022 · 17 (2) · 515-544
DOI: 10.1214/21-ba1259 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bayesian Analysis, erschienen am 01.06.2022. Verfasst von Hugh A. Chipman und 3 weiteren Autor:innen. Die Arbeit wurde bisher 39-mal zitiert (Crossref) und nennt 31 Literaturangaben.
Abstract (Originalsprache)
For the discovery of regression relationships between Y and a large set of p potential predictors x1,…,xp, the flexible nonparametric nature of BART (Bayesian Additive Regression Trees) allows for a much richer set of possibilities than restrictive parametric approaches. However, subject matter considerations sometimes warrant a minimal assumption of monotonicity in at least some of the predictors. For such contexts, we introduce mBART, a constrained version of BART that can flexibly incorporate monotonicity in any predesignated subset of predictors using a multivariate basis of monotone trees, while avoiding the further confines of a full parametric form. For such monotone relationships, mBART provides (i) function estimates that are smoother and more interpretable, (ii) better out-of-sample predictive performance, and (iii) less post-data uncertainty. While many key aspects of the unconstrained BART model carry over directly to mBART, the introduction of monotonicity constraints necessitates a fundamental rethinking of how the model is implemented. In particular, the original BART Markov Chain Monte Carlo algorithm relied on a conditional conjugacy that is no longer available in a monotonically constrained space. Various simulated and real examples demonstrate the wide ranging potential of mBART.
Zitieren
APA
Chipman, H. A., George, E. I., McCulloch, R. E., & Shively, T. S. (2022). mBART: Multidimensional Monotone BART. Bayesian Analysis, 17(2), 515-544. https://doi.org/10.1214/21-ba1259
Vancouver
Chipman HA, George EI, McCulloch RE, Shively TS. mBART: Multidimensional Monotone BART. Bayesian Analysis. 2022;17(2):515-544. doi:10.1214/21-ba1259
BibTeX
@article{Chipman2022,
author = {Chipman, Hugh A. and George, Edward I. and McCulloch, Robert E. and Shively, Thomas S.},
title = {mBART: Multidimensional Monotone BART},
journal = {Bayesian Analysis},
year = {2022},
volume = {17},
number = {2},
pages = {515--544},
doi = {10.1214/21-ba1259}
}
EUVIMED