Bounds for Bayesian order identification with application to mixtures

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.

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)

References in corpus (1)

• Testing the order of a model

Cited by in corpus (5)

• Finite mixture models do not reliably learn the number of components
• Non parametric finite translation mixtures with dependent regime
• Optimal Bayesian estimation of Gaussian mixtures with growing number of components
• Bayesian mixture models (in)consistency for the number of clusters
• On Bayesian Data Analysis