Accession Number:

ADA141985

Title:

An Application of Empirical Bayes Techniques to the Simultaneous Estimation of Many Probabilities

Descriptive Note:

Scientific rept.

Corporate Author:

GEORGE WASHINGTON UNIV WASHINGTON DC INST FOR MANAGEMENT SCIENCE AND ENGINEERING

Personal Author(s):

Report Date:

1984-05-03

Pagination or Media Count:

21.0

Abstract:

This document considers the following situation each of N different combat units is presented with a number of requirements to satisfy, each requirement being classified into one of K mutually exclusive categories. For each unit satisfying and requirement in that category is desired. The problem can be generally stated as that of estimating N different K-dimensional vectors of probabilities based upon a corresponding set of K-dimensional vectors of sample proportions. An empirical Bayes model is formulated and applied to an example from the Marine Corps Combat Readiness Evaluation System MCCRES. The EM algorithm provides a convenient method of estimating the prior parameters. The Bayes estimates are compared to the ordinary estimates, i.e. the sample proportions, by means of cross-validation and the Bayes estimates are shown to provide considerable improvement. Author

Subject Categories:

  • Statistics and Probability

Distribution Statement:

APPROVED FOR PUBLIC RELEASE