A unique estimate of linear regression function by least-absolute-deviations method

Authors
Cermak, V Henzler, J
Citation
V. Cermak et J. Henzler, A unique estimate of linear regression function by least-absolute-deviations method, J NONPARA S, 13(3), 2001, pp. 413-424
Citations number
5
Categorie Soggetti
Mathematics
Journal title
JOURNAL OF NONPARAMETRIC STATISTICS
ISSN journal
10485252 → ACNP
Volume
13
Issue
3
Year of publication
2001
Pages
413 - 424
Database
ISI
SICI code
1048-5252(2001)13:3<413:AUEOLR>2.0.ZU;2-N
Abstract
The purpose of this article is to fill a gap in the method of least absolut e deviations. While the method of least squares always gives a unique resul t, l.a.d., in some cases, does not. In literature and computer programs is the problem solved by convention. Our suggestion of unique estimation gener alizes one rather unknown definition of median for even number of observati on from [I].