A StahelDonoho estimator based on huberized outlyingnessA StahelDonoho estimator based on huberized outlyingness
Faculty of Sciences. Mathematics and Computer Science

Department of Mathematics - Computer Sciences

Department of Mathematics and Computer Science - other

article

2012Amsterdam, 2012

Mathematics

Computer. Automation

Computational statistics and data analysis. - Amsterdam

56(2012):3, p. 531-542

0167-9473

000298122600008

E

English (eng)

University of Antwerp

The StahelDonoho estimator is defined as a weighted mean and covariance, where the weight of each observation depends on a measure of its outlyingness. In high dimensions, it can easily happen that a number of outlying measurements are present in such a way that the majority of observations are contaminated in at least one of their components. In these situations, the StahelDonoho estimator has difficulties in identifying the actual outlyingness of the contaminated observations. An adaptation of the StahelDonoho estimator is presented in which the data are huberized before the outlyingness is computed. It is shown that the huberized outlyingness better reflects the actual outlyingness of each observation towards the non-contaminated observations. Therefore, the resulting adapted StahelDonoho estimator can better withstand large numbers of outliers. It is demonstrated that the StahelDonoho estimator based on huberized outlyingness works especially well when the data are heavily contaminated.

https://repository.uantwerpen.be/docman/iruaauth/e038e0/aaf0b3276a6.pdf

http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000298122600008&DestLinkType=RelatedRecords&DestApp=ALL_WOS&UsrCustomerID=ef845e08c439e550330acc77c7d2d848

http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000298122600008&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=ef845e08c439e550330acc77c7d2d848

http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000298122600008&DestLinkType=CitingArticles&DestApp=ALL_WOS&UsrCustomerID=ef845e08c439e550330acc77c7d2d848