ArticleOriginal scientific text
Title
Bayes robustness via the Kolmogorov metric
Authors 1, 2
Affiliations
- Faculty of Mathematics, University of Warsaw, Banacha 2, 02-097 Warszawa, Poland
- Institute of Mathematics, polish Academy of Sciences, P.O. Box 137, 00-950 Warszawa, Poland
Abstract
An upper bound for the Kolmogorov distance between the posterior distributions in terms of that between the prior distributions is given. For some likelihood functions the inequality is sharp. Applications to assessing Bayes robustness are presented.
Keywords
stability of Bayes procedures, Bayes robustness, Kolmogorov metric
Bibliography
- J. O. Berger (1985), Statistical Decision Theory and Bayesian Analysis, Springer
- J. O. Berger and L. M. Berliner (1986), Robust Bayes and empirical Bayes analysis with ε-contaminated priors, Ann. Statist. 14, 461-486
- A. E. Gelfand and D. K. Dey (1991), On Bayesian robustness of contaminated classes of priors, Statist. Decisions 9, 63-80
- M. Męczarski and R. Zieliński (1991), Stability of the Bayesian estimator of the Poisson mean under the inexactly specified gamma priors, Statist. Probab. Lett. 12, 329-333
- S. T. Rachev (1991), Probability Metrics and the Stability of Stochastic Models, Wiley, Chichester
- S. Sivaganesan (1988), Ranges of posterior measures for priors with arbitrary contamination, Comm. Statist. Theory Methods 17 (5), 1591-1612
- S. Sivaganesan and J. O. Berger (1989), Ranges of posterior measures for priors with unimodal contaminations, Ann. Statist. 17, 868-889
- V. M. Zolotarev (1986), Contemporary Theory of Summation of Independent Random Variables, Nauka, Moscow (in Russian)
Pages:
139-143
Main language of publication
English
Received
1993-07-01
Published
1993
Exact and natural sciences