A Minimax and Admissible Subset Selection Rule for the Least Probable Multinomial Cell.

Abstract

In this paper a new subset selection rule for selecting a subset containing the least probable multinomial cell is defined. The rule is shown to be minimax and admissible in the class of rules which have a preassigned probability of at least P* of selecting the least probable cell provided that P* is sufficiently large. The loss used is the number of non-best cells selected. (Author)

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 01, 1979
Accession Number
ADA080582

Entities

People

  • Roger L. Berger

Organizations

  • Florida State University

Tags

DTIC Thesaurus Topics

  • Data Science
  • Decision Theory
  • Inequalities
  • Information Science
  • Invariance
  • Military Research
  • Order Statistics
  • Probability
  • Probability Distributions
  • Statistical Decision Theory
  • Statistics
  • Theorems
  • Universities

Fields of Study

  • Mathematics

Readers

  • Regression Analysis.