Authors: Bernholt, Thorsten
Title: Robust Estimators are Hard to Compute
Language (ISO): en
Abstract: In modern statistics, the robust estimation of parameters of a re- gression hyperplane is a central problem. Robustness means that the estimation is not or only slightly a®ected by outliers in the data. In this paper, it is shown that the following robust estimators are hard to compute: LMS, LQS, LTS, LTA, MCD, MVE, Constrained M es- timator, Projection Depth (PD) and Stahel-Donoho. In addition, a data set is presented such that the ltsReg-procedure of R has proba- bility less than 0.0001 of ¯nding a correct answer. Furthermore, it is described, how to design new robust estimators.
Subject Headings: algorithms
complexity theory
computational statistics
robust statistics
search heuristics
URI: http://hdl.handle.net/2003/22138
http://dx.doi.org/10.17877/DE290R-14253
Issue Date: 2006-01-25T12:51:23Z
Appears in Collections:Sonderforschungsbereich (SFB) 475

Files in This Item:
File Description SizeFormat 
tr52-05.pdfDNB300.96 kBAdobe PDFView/Open


This item is protected by original copyright



All resources in the repository are protected by copyright.