A Comparison of Estimators for Regression Models with Change Points

34 Pages Posted: 30 Mar 2010

See all articles by Cathy W. S. Chen

Cathy W. S. Chen

Feng Chia University - Department of Statistics; Graduate Institute of Statistics & Actuarial Science, Feng Chia University

Jennifer S. K. Chan

The University of Sydney

Richard H. Gerlach

University of Sydney

William

Graduate Institute of Statistics & Actuarial Science, Feng Chia University

Date Written: March 26, 2010

Abstract

We consider two problems concerning locating change points in a linear regression model. One involves jump discontinuities (change-point) in a regression model and the other involves regression lines connected at unknown points. We compare four methods for estimating single or multiple change points in a regression model, when both the error variance and regression coefficients change simultaneously at the unknown point(s): Bayesian, Julious, grid search, and the segmented methods. The proposed methods are evaluated via a simulation study and compared via some standard measures of estimation bias and precision. Finally, the methods are illustrated and compared using three real data sets. The simulation and empirical results overall favor both the segmented and Bayesian methods of estimation, which simultaneously estimate the change point and the other model parameters, though only the Bayesian method is able to handle both continuous and dis-continuous change point problems successfully. If it is known that regression lines are continuous then the segmented method ranked first among methods.

Keywords: Change point, Jump discontinuities, MCMC, Grid-search, Segmented regression

JEL Classification: C11, C13, C21, C52

Suggested Citation

Chen, Cathy W. S. and Chan, Jennifer S. K. and Gerlach, Richard H. and Hsieh, William YL, A Comparison of Estimators for Regression Models with Change Points (March 26, 2010). Available at SSRN: https://ssrn.com/abstract=1579184 or http://dx.doi.org/10.2139/ssrn.1579184

Cathy W. S. Chen (Contact Author)

Feng Chia University - Department of Statistics ( email )

100 Wen Hwa Road
Taichung, 407
Taiwan
886 4 24517250 ext 4412 (Phone)
886 4 24517092 (Fax)

HOME PAGE: http://myweb.fcu.edu.tw/~chenws/

Graduate Institute of Statistics & Actuarial Science, Feng Chia University

100 Wenhwa Road
Talchung
Taiwan
886 4-24517250 ext 4412 (Phone)
886 4-2517092 (Fax)

HOME PAGE: http://myweb.fcu.edu.tw/~chenws/

Jennifer S. K. Chan

The University of Sydney ( email )

Sydney, New South Wales 2006
Australia

Richard H. Gerlach

University of Sydney ( email )

Room 483, Building H04
University of Sydney
Sydney, NSW 2006
Australia
+ 612 9351 3944 (Phone)
+ 612 9351 6409 (Fax)

HOME PAGE: http://www.econ.usyd.edu.au/staff/richardg

William YL Hsieh

Graduate Institute of Statistics & Actuarial Science, Feng Chia University ( email )

100 Wenhwa Road
Talchung
Taiwan

Register to save articles to
your library

Register

Paper statistics

Downloads
160
Abstract Views
712
rank
186,651
PlumX Metrics