Accession Number:

ADA393488

Title:

On Empirical Bayes Procedures for Selecting Good Populations in Positive Exponential Family

Descriptive Note:

Technical rept.

Corporate Author:

PURDUE UNIV LAFAYETTE IN DEPT OF STATISTICS

Personal Author(s):

Report Date:

2001-08-01

Pagination or Media Count:

23.0

Abstract:

The problem of selecting good ones compared with a control from kgreater than or equal to 2 positive exponential family populations is considered in this paper. A nonparametric empirical Bayes approach is used to construct the selection procedures. It has been shown that the risks of the empirical Bayes procedures converge to the minimum Bayes risk with a rate of O1n, where n is the number of accumulated past observations at hand. Simulations were carried out to study the performance of the procedures for small to moderate values of n. The results of this study are provided in the paper.

Subject Categories:

  • Statistics and Probability

Distribution Statement:

APPROVED FOR PUBLIC RELEASE