Posterior propriety and admissibility of hyperpriors in normal hierarchical models
Open Access
- 1 April 2005
- journal article
- Published by Institute of Mathematical Statistics in The Annals of Statistics
- Vol. 33 (2) , 606-646
- https://doi.org/10.1214/009053605000000075
Abstract
Hierarchical modeling is wonderful and here to stay, but hyperparameter priors are often chosen in a casual fashion. Unfortunately, as the number of hyperparameters grows, the effects of casual choices can multiply, leading to considerably inferior performance. As an extreme, but not uncommon, example use of the wrong hyperparameter priors can even lead to impropriety of the posterior. For exchangeable hierarchical multivariate normal models, we first determine when a standard class of hierarchical priors results in proper or improper posteriors. We next determine which elements of this class lead to admissible estimators of the mean under quadratic loss; such considerations provide one useful guideline for choice among hierarchical priors. Finally, computational issues with the resulting posterior distributions are addressed.Keywords
All Related Versions
This publication has 33 references indexed in Scilit:
- Bayesian correlation estimationBiometrika, 2004
- MinimaxityJournal of the American Statistical Association, 2000
- Hierarchical Models: A Current Computational PerspectiveJournal of the American Statistical Association, 2000
- An Essay on Statistical Decision TheoryJournal of the American Statistical Association, 2000
- Nonconjugate Bayesian Estimation of Covariance Matrices and its Use in Hierarchical ModelsJournal of the American Statistical Association, 1999
- Reference prior bayes estimator for bivariate normal covariance matrix with risk comparisonCommunications in Statistics - Theory and Methods, 1997
- Estimation of a Covariance Matrix Using the Reference PriorThe Annals of Statistics, 1994
- Outliers and Credence for Location Parameter InferenceJournal of the American Statistical Association, 1990
- A Robust Generalized Bayes Estimator and Confidence Region for a Multivariate Normal MeanThe Annals of Statistics, 1980
- Admissible Estimators, Recurrent Diffusions, and Insoluble Boundary Value ProblemsThe Annals of Mathematical Statistics, 1971