On some difficulties with a posterior probability approximation technique

Marin, Jean-Michel; Robert, Christian P.

Marin, Jean-Michel; Robert, Christian P. (2008), On some difficulties with a posterior probability approximation technique, Bayesian Analysis, 3, 2, p. 427-442. http://dx.doi.org/10.1214/08-BA316

Type

Article accepté pour publication ou publié

External document link

http://hal.inria.fr/inria-00260507/en/

Date

2008

Journal name

Bayesian Analysis

Volume

Number

Publisher

International Society for Bayesian Analysis

Pages

427-442

Abstract (EN)

In Scott (2002) and Congdon (2006), a new method is advanced to compute posterior probabilities of models under consideration. It is based solely on MCMC outputs restricted to single models, i.e., it is bypassing reversible jump and other model exploration techniques. While it is indeed possible to approximate posterior probabilities based solely on MCMC outputs from single models, as demonstrated by Gelfand and Dey (1994) and Bartolucci et al. (2006), we show that the proposals of Scott (2002) and Congdon (2006) are biased and advance several arguments towards this thesis, the primary one being the confusion between model-based posteriors and joint pseudo-posteriors.

Subjects / Keywords

Statistiques