Panel LM Unit Root Tests with Trend Shifts

34 Pages Posted: 3 Jun 2010

See all articles by Kyung So Im

Kyung So Im

affiliation not provided to SSRN

Junsoo Lee

University of Alabama - Department of Economics, Finance and Legal Studies

Margie Tieslau

University of North Texas - Department of Economics

Date Written: March 1, 2010

Abstract

This paper proposes a new Lagrange multiplier (LM) based unit root test for panel data allowing for heterogeneous structural breaks in both the intercept and slope of each cross-section unit in the panel. We note that panel unit root tests allowing for breaks in the slope will critically depend on the nuisance parameters indicating the size and location of breaks. Any panel tests that ignore this dependency on the nuisance parameter will be subject to serious size distortions. To address this problem, our test employs a method that renders the asymptotic distribution of the panel tests invariant to nuisance parameters. We derive the asymptotic properties of our test and also examine its finite-sample properties. In addition, our test easily can be modified to correct for the presence of cross-correlations in the innovations of the panel. We illustrate this by applying the cross-sectionally augmented ADF (CADF) procedure of Pesaran (2007) to our test statistic.

Keywords: Panel Unit Root Tests, LM Test, Structural Breaks, Trend Breaks

JEL Classification: C12, C15, C22

Suggested Citation

Im, Kyung So and Lee, Junsoo and Tieslau, Margie, Panel LM Unit Root Tests with Trend Shifts (March 1, 2010). Available at SSRN: https://ssrn.com/abstract=1619918 or http://dx.doi.org/10.2139/ssrn.1619918

Kyung So Im (Contact Author)

affiliation not provided to SSRN ( email )

Junsoo Lee

University of Alabama - Department of Economics, Finance and Legal Studies ( email )

P.O. Box 870244
Tuscaloosa, AL Alabama 35487
United States
2053488978 (Phone)

Margie Tieslau

University of North Texas - Department of Economics ( email )

Denton, TX 76203-1457
United States

Do you want regular updates from SSRN on Twitter?

Paper statistics

Downloads
204
Abstract Views
1,317
rank
203,160
PlumX Metrics