Reweighted Least Trimmed Squares: An Alternative to One-Step Estimators

CentER Discussion Paper Series No. 2010-100

35 Pages Posted: 2 Oct 2010

See all articles by Pavel Cizek

Pavel Cizek

Tilburg University - Department of Econometrics & Operations Research

Date Written: August 1, 2010

Abstract

A new class of robust regression estimators is proposed that forms an alternative to traditional robust one-step estimators and that achieves the √n rate of convergence irrespective of the initial estimator under a wide range of distributional assumptions. The proposed reweighted least trimmed squares (RLTS) estimator employs data-dependent weights determined from an initial robust fit. Just like many existing one- and two-step robust methods, the RLTS estimator preserves robust properties of the initial robust estimate. However contrary to existing methods, the first-order asymptotic behavior of RLTS is independent of the initial estimate even if errors exhibit heteroscedasticity, asymmetry, or serial correlation. Moreover, we derive the asymptotic distribution of RLTS and show that it is asymptotically efficient for normally distributed errors. A simulation study documents benefits of these theoretical properties in finite samples.

Keywords: Asymptotic Efficiency, Breakdown Point, Least Trimmed Squares

JEL Classification: C13, C21

Suggested Citation

Cizek, Pavel, Reweighted Least Trimmed Squares: An Alternative to One-Step Estimators (August 1, 2010). CentER Discussion Paper Series No. 2010-100, Available at SSRN: https://ssrn.com/abstract=1685903 or http://dx.doi.org/10.2139/ssrn.1685903

Pavel Cizek (Contact Author)

Tilburg University - Department of Econometrics & Operations Research ( email )

Tilburg, 5000 LE
Netherlands

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
106
Abstract Views
729
Rank
508,604
PlumX Metrics