Change search
ReferencesLink to record
Permanent link

Direct link
Algorithms to compute CM - and S-estimates for regression
Department of Mathematics, Cukurova University.
Luleå University of Technology, Department of Engineering Sciences and Mathematics, Mathematical Science.
2003 (English)In: International Conference on Robust Statistics: ICORS / [ed] Rudolf Dutter; P. Filzmoser; U. Gather; P. J. Pousseeuw, Physica-Verlag Rudolf Liebig GmbH , 2003, 62-76 p.Conference paper (Refereed)
Abstract [en]

Constrained M-estimators for regression were introduced by Mendes and Tyler in 1995 as an alternative class of robust regression estimators with high breakdown point and high asymptotic efficiency. To compute the CM-estimate, the global minimum of an objective function with an inequality constraint has to be localized. To find the S-estimate for the same problem, we instead restrict ourselves to the boundary of the feasible region. The algorithm presented for computing CM-estimates can easily be modified to compute S-estimates as well. Testing is carried out with a comparison to the algorithm SURREAL by Ruppert

Place, publisher, year, edition, pages
Physica-Verlag Rudolf Liebig GmbH , 2003. 62-76 p.
, Metrika, ISSN 0026-1335 ; 1-2
Research subject
Scientific Computing
URN: urn:nbn:se:ltu:diva-37223Local ID: b2e030f0-ac80-11db-aeba-000ea68e967bISBN: 3-7908-1518-7OAI: diva2:1010721
Developments in robust statistics : 23/07/2001 - 27/07/2001
Godkänd; 2003; 20070122 (evan)Available from: 2016-10-03 Created: 2016-10-03Bibliographically approved

Open Access in DiVA

fulltext(142 kB)0 downloads
File information
File name FULLTEXT01.pdfFile size 142 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Edlund, OveEkblom, Håkan
By organisation
Mathematical Science

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

ReferencesLink to record
Permanent link

Direct link