BartMixVs

Bayesian additive regression trees (BART) provides flexible non-parametric modeling of mixed-type predictors for continuous and binary responses. This package is built upon CRAN R package 'BART', version 2.7 (). It implements the three proposed variable selection approaches in the paper: Luo, C and Daniels, M. J. (2021), "Variable Selection Using Bayesian Additive Regression Trees." , and other three existing BART-based variable selection approaches.