Accession Number:

ADA190766

Title:

On Two-Stage Allocation Procedures for Selection Problems.

Descriptive Note:

Technical rept.,

Corporate Author:

PURDUE UNIV LAFAYETTE IN DEPT OF STATISTICS

Personal Author(s):

Report Date:

1987-12-08

Pagination or Media Count:

16.0

Abstract:

This paper deals with the problem of deriving two-stage allocation procedures for selecting the best normal population. If the prior distribution is assumed to be known, an exact Bayes two-stage allocation procedure is obtained. If the prior distribution depends on some unknown parameter, an adaptive two-stage allocation procedure is proposed. Using the empirical Bayes formulation, we prove that the proposed adaptive two-stage allocation procedure has some asymptotic optimallity property.

Subject Categories:

  • Statistics and Probability

Distribution Statement:

APPROVED FOR PUBLIC RELEASE