Asymptotics of Least Trimmed Squares Regression

Research output: Working paperDiscussion paperOther research output

251 Downloads (Pure)

Abstract

High breakdown-point regression estimators protect against large errors both in explanatory and dependent variables.The least trimmed squares (LTS) estimator is one of frequently used, easily understandable, and thoroughly studied (from the robustness point of view) high breakdown-point estimators.In spite of its increasing popularity and number of applications, there are only conjectures and hints about its asymptotic behavior in regression after two decades of its existence.We derive here all important asymptotic properties of LTS, including the asymptotic normality and variance, under mild B-mixing conditions.
Original languageEnglish
Place of PublicationTilburg
PublisherEconometrics
Number of pages53
Volume2004-72
Publication statusPublished - 2004

Publication series

NameCentER Discussion Paper
Volume2004-72

Fingerprint

Least Trimmed Squares
Breakdown Point
Regression
Estimator
Mixing Conditions
Regression Estimator
Asymptotic Variance
Asymptotic Normality
Asymptotic Properties
Asymptotic Behavior
Robustness
Dependent

Keywords

  • least squares
  • estimation
  • regression analysis

Cite this

Cizek, P. (2004). Asymptotics of Least Trimmed Squares Regression. (CentER Discussion Paper; Vol. 2004-72). Tilburg: Econometrics.
Cizek, P. / Asymptotics of Least Trimmed Squares Regression. Tilburg : Econometrics, 2004. (CentER Discussion Paper).
@techreport{dab5d551aca640bfb92ec0e1c9d66160,
title = "Asymptotics of Least Trimmed Squares Regression",
abstract = "High breakdown-point regression estimators protect against large errors both in explanatory and dependent variables.The least trimmed squares (LTS) estimator is one of frequently used, easily understandable, and thoroughly studied (from the robustness point of view) high breakdown-point estimators.In spite of its increasing popularity and number of applications, there are only conjectures and hints about its asymptotic behavior in regression after two decades of its existence.We derive here all important asymptotic properties of LTS, including the asymptotic normality and variance, under mild B-mixing conditions.",
keywords = "least squares, estimation, regression analysis",
author = "P. Cizek",
note = "Subsequently published in the Journal of Statistical Planning & Inference, 2006 Pagination: 53",
year = "2004",
language = "English",
volume = "2004-72",
series = "CentER Discussion Paper",
publisher = "Econometrics",
type = "WorkingPaper",
institution = "Econometrics",

}

Cizek, P 2004 'Asymptotics of Least Trimmed Squares Regression' CentER Discussion Paper, vol. 2004-72, Econometrics, Tilburg.

Asymptotics of Least Trimmed Squares Regression. / Cizek, P.

Tilburg : Econometrics, 2004. (CentER Discussion Paper; Vol. 2004-72).

Research output: Working paperDiscussion paperOther research output

TY - UNPB

T1 - Asymptotics of Least Trimmed Squares Regression

AU - Cizek, P.

N1 - Subsequently published in the Journal of Statistical Planning & Inference, 2006 Pagination: 53

PY - 2004

Y1 - 2004

N2 - High breakdown-point regression estimators protect against large errors both in explanatory and dependent variables.The least trimmed squares (LTS) estimator is one of frequently used, easily understandable, and thoroughly studied (from the robustness point of view) high breakdown-point estimators.In spite of its increasing popularity and number of applications, there are only conjectures and hints about its asymptotic behavior in regression after two decades of its existence.We derive here all important asymptotic properties of LTS, including the asymptotic normality and variance, under mild B-mixing conditions.

AB - High breakdown-point regression estimators protect against large errors both in explanatory and dependent variables.The least trimmed squares (LTS) estimator is one of frequently used, easily understandable, and thoroughly studied (from the robustness point of view) high breakdown-point estimators.In spite of its increasing popularity and number of applications, there are only conjectures and hints about its asymptotic behavior in regression after two decades of its existence.We derive here all important asymptotic properties of LTS, including the asymptotic normality and variance, under mild B-mixing conditions.

KW - least squares

KW - estimation

KW - regression analysis

M3 - Discussion paper

VL - 2004-72

T3 - CentER Discussion Paper

BT - Asymptotics of Least Trimmed Squares Regression

PB - Econometrics

CY - Tilburg

ER -

Cizek P. Asymptotics of Least Trimmed Squares Regression. Tilburg: Econometrics. 2004. (CentER Discussion Paper).