Credible Means Are Exact Bayesian for Exponential Families.

reportActive / Technical Report | Accession Number: AD0770626 | Need Help?

Abstract:

The credibility formula used in casualty insurance experience rating is known to be exact for certain prior-likelihood distributions, and, the minimum least-squares unbiased estimator for all others. The author shows that credibility is also exact for all simple exponential families,and is also true in an extended sense for all regular distributions with a fixed-dimensional sufficient statistic. Author

Author(s):
Jewell, William S.
Author Organization(s):
CALIFORNIA UNIV BERKELEY OPERATIONS RESEARCH CENTER
Descriptive Note:
Research rept.,
Supplementary Note:
Paper presented at ASTIN Colloquium (10th), 4-8 Sep 73, Colchester (England).
Pagination:
0026

Security Markings

DOCUMENT & CONTEXTUAL SUMMARY

Distribution:
Approved For Public Release

RECORD

Collection: TR
Identifying Numbers
Report Number(s):
ORC-73-21, AROD-5307.77-M
Contract/Grant Number(s):
N00014-69-A-0200-1010, DA-31-124-ARO(D)-331
Task Number(s):
RR0030701
Project Number(s):
NR-047-033, RR003-07
Monitor Series:
5307.77-M
 Subject Terms
Communities of Interest:
No COI(s) Identified
Descriptor(s):
*Economics, *Statistical distributions, *Bayes theorem, *Risk, Sampling, Exponential functions, Mathematical models
Field(s)/Group(s):
Economics and Cost Analysis, Operations Research
Keyword(s):
*Credibility theory, *Insurance, Bayesian analysis
Report Date:
1973 Oct 01