Shrinkage priors for Bayesian prediction
Author:
- Fumiyasu KomakiFKFumiyasu Komaki
Preprint
Abstract
We investigate shrinkage priors for constructing Bayesian predictive distributions. It is shown that there exist shrinkage predictive distributions asymptotically dominating Bayesian predictive distributions based on the Jeffreys prior or other vague priors if the model manifold satisfies some differential geometric conditions. Kullback--Leibler divergence from the true distribution to a predictive distribution is adopted as a loss function. Conformal transformations of model manifolds corresponding to vague priors are introduced. We show several examples where shrinkage predictive distributions dominate Bayesian predictive distributions based on vague priors.Keywords
All Related Versions
- Version 1, 2006-07-01, ArXiv
- Published version: The Annals of Statistics, 34 (2), 808.
This publication has 15 references indexed in Scilit:
- Shrinkage priors for Bayesian predictionThe Annals of Statistics, 2006
- Improved minimax predictive densities under Kullback–Leibler lossThe Annals of Statistics, 2006
- Simultaneous prediction of independent Poisson observablesThe Annals of Statistics, 2004
- Bayesian Predictive Distribution with Right Invariant PriorsCalcutta Statistical Association Bulletin, 2002
- A shrinkage predictive distribution for multivariate Normal observablesBiometrika, 2001
- Bayesian prediction with approximate frequentist validityThe Annals of Statistics, 2000
- On asymptotic properties of predictive distributionsBiometrika, 1996
- Heat Kernels and Spectral Theory1989
- Minimax Estimation and Positive Solutions of Elliptic EquationsTheory of Probability & Its Applications, 1983
- Admissible Estimators, Recurrent Diffusions, and Insoluble Boundary Value ProblemsThe Annals of Mathematical Statistics, 1971