L1-estimation in linear models with heterogeneous white noise

Necessary and sufficient conditions are given for the consistency of the L1-estimator of the regression parameter [beta] in linear models with independent but possibly nonidentically distributed errors. The heteroscedastic case is treated as a particular case. The asymptotic normality of is also established, under assumptions which are weaker than in related results on the asymptotics of the sample median in heteroscedastic location models.

MoreLess

Year of publication:	1999
Authors:	Bantli, Faouzi El ; Hallin, Marc
Published in:	Statistics & Probability Letters. - Elsevier, ISSN 0167-7152. - Vol. 45.1999, 4, p. 305-315
Publisher:	Elsevier
Subject:	L1-estimation Heterogeneity Heteroscedasticity Linear model

More details

Type of publication:	Article
Source:	RePEc - Research Papers in Economics

Persistent link: https://www.econbiz.de/10005223207