Premium
Classification Procedures Based on Bayes's Formula
Author(s) -
Birnbaum A.,
Maxwell A. E.
Publication year - 1960
Publication title -
journal of the royal statistical society: series c (applied statistics)
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.205
H-Index - 72
eISSN - 1467-9876
pISSN - 0035-9254
DOI - 10.2307/2985716
Subject(s) - bayes' theorem , mathematics , statistics , computer science , bayesian probability
In this article Dr Birnbaum and Dr Maxwell describe some methods of classification based on the classical probability formula of Bayes, and on some of its applications suggested by the theory of statistical decision functions. The classification problems considered are general, utilising no restrictive assumptions about possible distribution forms, but assuming that distributions can be estimated from large samples of data. The method is illustrated by an exploratory application to preliminary diagnostic classification, using data on 772 patients of a psychiatric hospital.