Bayes and empirical Bayes : Do they merge?
Scricciolo, Catia; Rousseau, Judith; Petrone, Sonia (2014), Bayes and empirical Bayes : Do they merge?, Biometrika, 101, 2, p. 285-302. http://dx.doi.org/10.1093/biomet/ast067
TypeArticle accepté pour publication ou publié
External document linkhttp://hal.archives-ouvertes.fr/hal-00767467
Oxford University Press
MetadataShow full item record
Abstract (EN)Bayesian inference is attractive for its coherence and good frequentist properties. However, eliciting a honest prior may be difficult and a common practice is to take an empirical Bayes approach, using some empirical estimate of the prior hyperparameters. Despite not rigorous, the underlying idea is that, for sufficiently large sample size, empirical Bayes leads to similar inferential answers as a proper Bayesian inference. However, precise mathematical results seem missing. In this work, we give more rigorous results in terms of merging of Bayesian and empirical Bayesian posterior distributions. We study two notions of merging: Bayesian weak merging and frequentist merging in total variation. We also show that, under regularity conditions, empirical Bayes asymptotically gives an oracle selection of the prior hyperparameters. Examples include empirical Bayes density estimation with Dirichlet process mixtures.
Subjects / KeywordsDirichlet process mixtures; Maximum marginal likelihood estimate; Frequentist strong merging; Bayesian weak merging; Consistency
Showing items related by title and author.
Posterior concentration rates for empirical Bayes procedures, with applications to Dirichlet Process mixtures Donnet, Sophie; Rivoirard, Vincent; Rousseau, Judith; Scricciolo, Catia (2018) Article accepté pour publication ou publié
Posterior concentration rates for empirical Bayes procedures, with applications to Dirichlet Process mixtures. Supplementary material Donnet, Sophie; Rivoirard, Vincent; Rousseau, Judith; Scricciolo, Catia (2014) Document de travail / Working paper
On some aspects of the asymptotic properties of Bayesian approaches in nonparametric and semiparametric models Scricciolo, Catia; Salomond, Jean-Bernard; Rousseau, Judith (2014-01-30) Communication / Conférence