Access the full text.
Sign up today, get DeepDyve free for 14 days.
Loading next page...
/lp/wiley/a-generalized-bayes-rule-for-prediction-J0oBSQOrgJ
References (19)
-
T. Irony, N. Singpurwalla (1997)
Non-informative priors do not exist A dialogue with José M. BernardoJournal of Statistical Planning and Inference, 65
-
J. Bjørnstad (1990)
Predictive Likelihood: A ReviewStatistical Science, 5
-
(1967)
Information - type measures of difference of probability distributions and indirect observations -
J. Aitchison (1975)
Goodness of prediction fitBiometrika, 62
-
O. Barndorff-Nielsen, D. Cox (1996)
Prediction and asymptoticsBernoulli, 2
-
G. Murray (1977)
NOTE ON ESTIMATION OF PROBABILITY DENSITY FUNCTIONS -
J. Corcuera, F. Giummolè (1999)
On the relationship between alpha-connections and the asymptotic properties of predictive distributionsBernoulli, 5
-
M. Lawera (1995)
Predictive inference : an introduction -
F. Komaki (1996)
On asymptotic properties of predictive distributionsBiometrika, 83
-
P. Dawid, J. Aitchison, I. Dunsmore (1975)
Statistical Prediction Analysis -
H. Akaike (1978)
A new look at the Bayes procedureBiometrika, 65
-
Ian Harris (1989)
Predictive fit for natural exponential familiesBiometrika, 76
-
G. El‐Sayyad, M. Samuddin, A. Al-Harbey (1989)
On parametric density estimationBiometrika, 76
-
(1981)
Likelihood prediction. Istit. Naz. Alta Mate -
I. Dunsmore, S. Geisser (1995)
8. Predictive Inference: An IntroductionJournal of The Royal Statistical Society Series A-statistics in Society, 158
-
J. Corcuera, Federica Giummole (1998)
A Characterization of Monotone and Regular DivergencesAnnals of the Institute of Statistical Mathematics, 50
-
S. Amari (1985)
Differential-geometrical methods in statistics -
J. Bjørnstad (1996)
On the Generalization of the Likelihood Function and the Likelihood PrincipleJournal of the American Statistical Association, 91
-
J. Hartigan (1965)
THE ASYMPTOTICALLY UNBIASED PRIOR DISTRIBUTIONAnnals of Mathematical Statistics, 36
- Publisher
- Wiley
- Copyright
- Board of the Foundation of the Scandinavian Journal of Statistics 1999
- ISSN
- 0303-6898
- eISSN
- 1467-9469
- DOI
- 10.1111/1467-9469.00149
- Publisher site
- See Article on Publisher Site
Abstract
In the case of prior knowledge about the unknown parameter, the Bayesian predictive density coincides with the Bayes estimator for the true density in the sense of the Kullback‐Leibler divergence, but this is no longer true if we consider another loss function. In this paper we present a generalized Bayes rule to obtain Bayes density estimators with respect to any α‐divergence, including the Kullback‐Leibler divergence and the Hellinger distance. For curved exponential models, we study the asymptotic behaviour of these predictive densities. We show that, whatever prior we use, the generalized Bayes rule improves (in a non‐Bayesian sense) the estimative density corresponding to a bias modification of the maximum likelihood estimator. It gives rise to a correspondence between choosing a prior density for the generalized Bayes rule and fixing a bias for the maximum likelihood estimator in the classical setting. A criterion for comparing and selecting prior densities is also given.
Journal
Scandinavian Journal of Statistics – Wiley
Published: Jun 1, 1999