首页   按字顺浏览 期刊浏览 卷期浏览 Mixture Models, Outliers, and the EM Algorithm
Mixture Models, Outliers, and the EM Algorithm

 

作者: Murray Aitkin,   GranvilleTunnicliffe Wilson,  

 

期刊: Technometrics  （Taylor Available online 1980）
卷期: Volume 22, issue 3  

页码: 325-331

 

ISSN:0040-1706

 

年代: 1980

 

DOI:10.1080/00401706.1980.10486163

 

出版商: Taylor & Francis Group

 

关键词: Outliers;Mixtures;Regression;EM algorithm

 

数据来源: Taylor

 

摘要:

Maximum likelihood (ML) methods are described for the identification of outliers in single sample or regression problems, based on mixture models. The EM algorithm provides a simple and easily programmed iterative solution for the ML estimates of the parameters in the models. The procedure is illustrated on three examples.

 

点击下载:  PDF (613KB)



返 回