Bounds for Bayesian order identification with application to mixtures

Antoine Chambaz; Judith Rousseau

doi:10.1214/009053607000000857

Bounds for Bayesian order identification with application to mixtures

Statistics Theory 2008-12-18 v1 Statistics Theory

Authors: Antoine Chambaz , Judith Rousseau

View on arXiv ↗ PDF ↗ DOI ↗

Abstract

The efficiency of two Bayesian order estimators is studied. By using nonparametric techniques, we prove new underestimation and overestimation bounds. The results apply to various models, including mixture models. In this case, the errors are shown to be $O(e^{-an})$ and $O((\log n)^b/\sqrt{n})$ ( $a,b>0$ ), respectively.

Keywords

upper bounds model selection

Cite

@article{arxiv.0804.0768,
  title  = {Bounds for Bayesian order identification with application to mixtures},
  author = {Antoine Chambaz and Judith Rousseau},
  journal= {arXiv preprint arXiv:0804.0768},
  year   = {2008}
}

Comments

Published in at http://dx.doi.org/10.1214/009053607000000857 the Annals of Statistics (http://www.imstat.org/aos/) by the Institute of Mathematical Statistics (http://www.imstat.org)

Bounds for Bayesian order identification with application to mixtures

Abstract

Keywords

Cite

Comments

Related papers