mBART: multidimensional monotone BART
From MaRDI portal
Publication:6202919
Abstract: For the discovery of regression relationships between Y and a large set of p potential predictors x 1 , . . . , x p , 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.
Recommendations
- BART: Bayesian additive regression trees
- Bayesian additive regression trees with model trees
- A method for Bayesian monotonic multiple regression
- Log-linear Bayesian additive regression trees for multinomial logistic and count regression models
- Variable selection for BART: an application to gene regulation
Cites work
- scientific article; zbMATH DE number 3930122 (Why is no real title available?)
- scientific article; zbMATH DE number 3390139 (Why is no real title available?)
- A Bayesian approach to non-parametric monotone function estimation
- A method for Bayesian monotonic multiple regression
- A nonparametric Bayes method for isotonic regression
- BART: Bayesian additive regression trees
- Bayesian Isotonic Regression and Trend Analysis
- Bayesian Multivariate Isotonic Regression Splines
- Bayesian analysis of shape-restricted functions using Gaussian process priors
- Bayesian estimation and inference for generalised partial linear models using shape-restricted splines
- Bayesian monotone regression using Gaussian process projection
- Bayesian regression tree ensembles that adapt to smoothness and sparsity
- Concentration rate and consistency of the posterior distribution for selected priors under monotonicity constraints
- Correcting an estimator of a multivariate monotone function with isotonic regression
- Estimating Smooth Monotone Functions
- Estimating a smooth monotone regression function
- Estimating shape constrained functions using Gaussian processes
- Generalized additive and index models with shape constraints
- Improving point and interval estimators of monotone functions by rearrangement
- Monotone Smoothing with Application to Dose-Response Curve
- Nonparametric function estimation subject to monotonicity, convexity and other shape constraints
- Posterior concentration for Bayesian regression trees and forests
- Variable selection for BART: an application to gene regulation
This page was built for publication: mBART: multidimensional monotone BART
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6202919)
