On Empirical Bayes Procedures for Selecting Good Populations in Positive Exponential Family
Abstract
The problem of selecting good ones compared with a control from k(greater 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 O(1/n), 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.
Document Details
- Document Type
- Technical Report
- Publication Date
- Aug 01, 2001
- Accession Number
- ADA393488
Entities
People
- Jianjun Li
- Shanti Gupta
Organizations
- Purdue University