Open Access
Translator Disclaimer
January, 1977 Classification by Maximum Posterior Probability
C. P. Shapiro
Ann. Statist. 5(1): 185-190 (January, 1977). DOI: 10.1214/aos/1176343752

Abstract

The problem of classifying each of $n$ observations to one of two sub-populations is considered. The classification rule examined chooses that classification with maximum posterior probability. Limiting behavior of the rule is given and several examples are presented which show that the rule can lead to classifying all observations to the same subpopulation. Three simulation studies are reported to indicate that this extreme behavior may occur in small samples.

Citation

Download Citation

C. P. Shapiro. "Classification by Maximum Posterior Probability." Ann. Statist. 5 (1) 185 - 190, January, 1977. https://doi.org/10.1214/aos/1176343752

Information

Published: January, 1977
First available in Project Euclid: 12 April 2007

zbMATH: 0364.62062
MathSciNet: MR431530
Digital Object Identifier: 10.1214/aos/1176343752

Subjects:
Primary: 62C10
Secondary: 62E20

Keywords: Bayesian , ‎classification‎

Rights: Copyright © 1977 Institute of Mathematical Statistics

JOURNAL ARTICLE
6 PAGES


SHARE
Vol.5 • No. 1 • January, 1977
Back to Top