The Equivalence of Two Rules of Classification for Two Populations
作者:
W.Kenneth Poole,
期刊:
The American Statistician
(Taylor Available online 1980)
卷期:
Volume 34,
issue 1
页码: 55-55
ISSN:0003-1305
年代: 1980
DOI:10.1080/00031305.1980.10482715
出版商: Taylor & Francis Group
关键词: Classification rules;Conditional expectation;Conditional probability
数据来源: Taylor
摘要:
In many applied classification problems, the populations of interest are defined in terms of ranges for the dependent variable. In these situations, it is intuitively appealing to classify individuals into the respective populations based on their estimated conditional expectation. On the other hand, based on theoretical considerations, one may wish to use the classification rule based on the posterior probabilities. This article shows that under certain conditions these two classification rules are equivalent.
点击下载:
PDF (104KB)
返 回