BART: Bayesian Additive Regression Trees

Bayesian Additive Regression Trees (BART) provide flexible nonparametric modeling of covariates for continuous, binary and time-to-event outcomes. For more information on BART, see Chipman, George and McCulloch (2010) <doi:10.1214/09-AOAS285> and Sparapani, Logan, McCulloch and Laud (2016) <doi:10.1002/sim.6893>.

Version: 1.6
Depends: R (≥ 2.10), survival
Imports: Rcpp (≥ 0.12.3), parallel, tools
LinkingTo: Rcpp
Suggests: knitr, rmarkdown, sbart, MASS
Published: 2018-03-20
Author: Robert McCulloch [aut], Rodney Sparapani [aut, cre], Robert Gramacy [aut], Charles Spanbauer [aut], Matthew Pratola [aut], Jean-Sebastien Roy [ctb], Makoto Matsumoto [ctb], Takuji Nishimura [ctb], Bill Venables [ctb], Brian Ripley [ctb]
Maintainer: Rodney Sparapani <rsparapa at mcw.edu>
License: GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]
NeedsCompilation: yes
SystemRequirements: C++11
Materials: NEWS
In views: MachineLearning
CRAN checks: BART results

Downloads:

Reference manual: BART.pdf
Vignettes: wbart, BART for Numeric Outcomes
Binary and categorical outcomes with BART
Efficient computing with BART
Continuous outcomes with BART: Part 1
Continuous outcomes with BART: Part 2
Time-to-event outcomes with BART
Package source: BART_1.6.tar.gz
Windows binaries: r-devel: BART_1.6.zip, r-release: BART_1.6.zip, r-oldrel: BART_1.6.zip
OS X binaries: r-release: BART_1.6.tgz, r-oldrel: BART_1.6.tgz
Old sources: BART archive

Linking:

Please use the canonical form https://CRAN.R-project.org/package=BART to link to this page.