Skip to main content
Article
Optimal-Partitioning Inequalities in Classification and Multi-Hypotheses Testing
The Annals of Probability
  • Theodore P. Hill, Georgia Institute of Technology - Main Campus
  • Y. L. Tong, Georgia Institute of Technology - Main Campus
Publication Date
9-1-1989
Abstract

Optimal-partitioning and minimax risk inequalities are obtained for the classification and multi-hypotheses testing problems. Best possible bounds are derived for the minimax risk for location parameter families, based on the tail concentrations and Levy concentrations of the distributions. Special attention is given to continuous distributions with the maximum likelihood ratio property and to symmetric unimodal continuous distributions. Bounds for general (including discontinuous) distributions are also obtained.

Disciplines
Citation Information
Theodore P. Hill and Y. L. Tong. "Optimal-Partitioning Inequalities in Classification and Multi-Hypotheses Testing" The Annals of Probability Vol. 17 Iss. 3 (1989) p. 1325 - 1334
Available at: http://works.bepress.com/tphill/2/