We propose general procedures for posterior sampling from additive
and generalized additive models. The procedure is a stochastic generalization
of the well-known backfitting algorithm for fitting additive models. One
chooses a linear operator (“smoother”) for each predictor, and
the algorithm requires only the application of the operator and its square
root. The procedure is general and modular, and we describe its application to
nonparametric, semiparametric and mixed models.
Publié le : 2000-08-01
Classification:
Additive models,
back fitting,
Bayes,
Gibbs sampling,
random effects,
Metropolis–Hastings procedure
@article{1009212815,
author = {Hastie, Trevor and Tibshirani, Robert},
title = {Bayesian backfitting (with comments and a rejoinder by the
authors},
journal = {Statist. Sci.},
volume = {15},
number = {1},
year = {2000},
pages = { 196-223},
language = {en},
url = {http://dml.mathdoc.fr/item/1009212815}
}
Hastie, Trevor; Tibshirani, Robert. Bayesian backfitting (with comments and a rejoinder by the
authors. Statist. Sci., Tome 15 (2000) no. 1, pp. 196-223. http://gdmltest.u-ga.fr/item/1009212815/