On Subset Selection Procedures for the Largest Mean from Normal Populations Having a Common Known Coefficient of Variation.
Abstract
The problem of selecting a subset of k normal populations which includes the population associated with the largest mean is considered for the situation in which the normal populations have a common known coefficient of variation. Subset selection rules based on best asymptotically normal (BAN) estimators of the mean have been studied in the literature and tables based on large sample theory for implementing these rules exist. The authors have compared these rules to a selection rule based on sample variances, and limited study suggest that, when n is large, the difference between the rules based on BAN estimates and the variance rule, in terms of the expected proportion of the selected subset, is minimal. Moreover, since the exact distribution theory for BAN estimates is too complicated, and these BAN estimates are much harder to compute than the sample variances, the selection rule based on the sample variances may be preferred. (Author)
Document Details
- Document Type
- Technical Report
- Publication Date
- Mar 01, 1983
- Accession Number
- ADA127136
Entities
People
- Ashok K. Singh
- Shanti Gupta
Organizations
- Purdue University