TY - JOUR
T1 - FULLY NONPARAMETRIC BAYESIAN ADDITIVE REGRESSION TREES
AU - George, Edward
AU - Laud, Purushottam
AU - Logan, Brent
AU - McCulloch, Robert
AU - Sparapani, Rodney
N1 - Publisher Copyright:
© 2019 by Emerald Publishing Limited
PY - 2019
Y1 - 2019
N2 - Bayesian additive regression trees (BART) is a fully Bayesian approach to modeling with ensembles of trees. BART can uncover complex regression functions with high-dimensional regressors in a fairly automatic way and provide Bayesian quantification of the uncertainty through the posterior. However, BART assumes independent and identical distributed (i.i.d) normal errors. This strong parametric assumption can lead to misleading inference and uncertainty quantification. In this chapter we use the classic Dirichlet process mixture (DPM) mechanism to nonparametrically model the error distribution. A key strength of BART is that default prior settings work reasonably well in a variety of problems. The challenge in extending BART is to choose the parameters of the DPM so that the strengths of the standard BART approach is not lost when the errors are close to normal, but the DPM has the ability to adapt to non-normal errors.
AB - Bayesian additive regression trees (BART) is a fully Bayesian approach to modeling with ensembles of trees. BART can uncover complex regression functions with high-dimensional regressors in a fairly automatic way and provide Bayesian quantification of the uncertainty through the posterior. However, BART assumes independent and identical distributed (i.i.d) normal errors. This strong parametric assumption can lead to misleading inference and uncertainty quantification. In this chapter we use the classic Dirichlet process mixture (DPM) mechanism to nonparametrically model the error distribution. A key strength of BART is that default prior settings work reasonably well in a variety of problems. The challenge in extending BART is to choose the parameters of the DPM so that the strengths of the standard BART approach is not lost when the errors are close to normal, but the DPM has the ability to adapt to non-normal errors.
UR - http://www.scopus.com/inward/record.url?scp=85135159674&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85135159674&partnerID=8YFLogxK
U2 - 10.1108/S0731-90532019000040B006
DO - 10.1108/S0731-90532019000040B006
M3 - Article
AN - SCOPUS:85135159674
SN - 0731-9053
VL - 40B
SP - 89
EP - 110
JO - Advances in Econometrics
JF - Advances in Econometrics
ER -