Robust linear regression via bounded influence M-estimators

We investigate optimal bounded influence M-estimators in the general normal regression model with respect to different sensitivities. As a result, we answer some open questions in F. R. Hampel et al. (Robust Statistics, Chap. 6, Wiley, New York). Moreover, we examine the relationship among different sensitives and their associated optimal estimators and extend the idea of change- of -variance sensitivity to the case of the predicted value.

MoreLess

Year of publication:	1992
Authors:	Cheng, Chi-Lun
Published in:	Journal of Multivariate Analysis. - Elsevier, ISSN 0047-259X. - Vol. 40.1992, 1, p. 158-171
Publisher:	Elsevier
Keywords:	robust regression influence function sensitivity change-of-variance function

More details

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

Persistent link: https://www.econbiz.de/10005152900