Empirical Bayes Rules for Selecting Good Populations.
Abstract
A problem of selecting populations better than a control is considered. When the populations are uniformly distributed, empirical Bayes rules are derived for a linear loss function for both the known control parameter and the unknown control parameter cases. When the priors are assumed to have bounded supports, empirical Bayes rules for selecting good populations are derived for distributions with truncation parameters (i.e. the form of the pdf is f(x/theta) = Pi(x)ci(theta)I(O, theta)(x)). Monte Carlo studies are carried out which determine the minimum sample sizes needed to make the relative errors less than epsilon for given epsilon-values. (Author)
Document Details
- Document Type
- Technical Report
- Publication Date
- Mar 01, 1981
- Accession Number
- ADA097619
Entities
People
- Ping Hsiao
- Shanti Gupta
Organizations
- Purdue University