Skip to main content
Journal cover image

Some Bayesian predictive approaches to model selection

Publication ,  Journal Article
Mukhopadhyay, N; Ghosh, JK; Berger, JO
Published in: Statistics and Probability Letters
July 15, 2005

A variety of pseudo-Bayes factors have been proposed, based on using part of the data to update an improper prior, and using the remainder of the data to compute the Bayes factor. A number of these approaches are of a bootstrap or cross-validation nature, with some type of average being taken over the data used for updating. Asymptotic characteristics of a number of these pseudo-Bayes factors are discussed, and it is shown how many behave quite differently from ordinary Bayes factors. It is also shown that arguments of predictive optimality, based on simply inserting the empirical distribution in place of the 'true predictive distribution', can be misleading; the particular example of this that is studied is the argument given in Bernardo and Smith [1994. Bayesian Theory. Wiley, Chichester] to the effect that the geometric intrinsic Bayes factor has an optimal predictive property. © 2005 Elsevier B.V. All rights reserved.

Duke Scholars

Published In

Statistics and Probability Letters

DOI

ISSN

0167-7152

Publication Date

July 15, 2005

Volume

73

Issue

4

Start / End Page

369 / 379

Related Subject Headings

  • Statistics & Probability
  • 4905 Statistics
  • 3802 Econometrics
  • 1403 Econometrics
  • 0104 Statistics
  • 0102 Applied Mathematics
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Mukhopadhyay, N., Ghosh, J. K., & Berger, J. O. (2005). Some Bayesian predictive approaches to model selection. Statistics and Probability Letters, 73(4), 369–379. https://doi.org/10.1016/j.spl.2005.04.012
Mukhopadhyay, N., J. K. Ghosh, and J. O. Berger. “Some Bayesian predictive approaches to model selection.” Statistics and Probability Letters 73, no. 4 (July 15, 2005): 369–79. https://doi.org/10.1016/j.spl.2005.04.012.
Mukhopadhyay N, Ghosh JK, Berger JO. Some Bayesian predictive approaches to model selection. Statistics and Probability Letters. 2005 Jul 15;73(4):369–79.
Mukhopadhyay, N., et al. “Some Bayesian predictive approaches to model selection.” Statistics and Probability Letters, vol. 73, no. 4, July 2005, pp. 369–79. Scopus, doi:10.1016/j.spl.2005.04.012.
Mukhopadhyay N, Ghosh JK, Berger JO. Some Bayesian predictive approaches to model selection. Statistics and Probability Letters. 2005 Jul 15;73(4):369–379.
Journal cover image

Published In

Statistics and Probability Letters

DOI

ISSN

0167-7152

Publication Date

July 15, 2005

Volume

73

Issue

4

Start / End Page

369 / 379

Related Subject Headings

  • Statistics & Probability
  • 4905 Statistics
  • 3802 Econometrics
  • 1403 Econometrics
  • 0104 Statistics
  • 0102 Applied Mathematics