TU Darmstadt / ULB / TUbiblio

Seasonal Unit Root Tests under Structural Breaks

Hassler, Uwe and Rodrigues, Paulo M. M. (2002):
Seasonal Unit Root Tests under Structural Breaks.
Darmstadt, In: Darmstadt Discussion Papers in Economics, [Online-Edition: http://econstor.eu/bitstream/10419/84842/1/ddpie_113.pdf],
[Report]

Abstract

In this paper, several seasonal unit root tests are analysed in the context of structural breaks at known time and a new break corrected test is suggested. We show that the widely used HEGY test as well as an LM variant thereof are asymptotically robust to seasonal mean shifts of finite magnitude. In finite samples, however, experiments reveal that such tests suffer from severe size distortions and power reductions when breaks are present. Hence, a new break corrected LM test is proposed in order to overcome this problem. Importantly, the correction for seasonal mean shifts bears no consequence on the limiting distributions thereby maintaining the legitimacy of canonical critical values. Moreover, although this test assumes a breakpoint a priori, it is robust in terms of misspecification of the time of the break. This asymptotic property is well reproduced in finite samples. Based on a Monte Carlo study, our new test is compared with other procedures suggested in the literature and shown to hold superior finite sample properties.

Item Type: Report
Erschienen: 2002
Creators: Hassler, Uwe and Rodrigues, Paulo M. M.
Title: Seasonal Unit Root Tests under Structural Breaks
Language: English
Abstract:

In this paper, several seasonal unit root tests are analysed in the context of structural breaks at known time and a new break corrected test is suggested. We show that the widely used HEGY test as well as an LM variant thereof are asymptotically robust to seasonal mean shifts of finite magnitude. In finite samples, however, experiments reveal that such tests suffer from severe size distortions and power reductions when breaks are present. Hence, a new break corrected LM test is proposed in order to overcome this problem. Importantly, the correction for seasonal mean shifts bears no consequence on the limiting distributions thereby maintaining the legitimacy of canonical critical values. Moreover, although this test assumes a breakpoint a priori, it is robust in terms of misspecification of the time of the break. This asymptotic property is well reproduced in finite samples. Based on a Monte Carlo study, our new test is compared with other procedures suggested in the literature and shown to hold superior finite sample properties.

Series Name: Darmstadt Discussion Papers in Economics
Volume: 113
Place of Publication: Darmstadt
Uncontrolled Keywords: Structural Breaks, Unit Roots, Seasonal Unit Root Tests
Divisions: 01 Department of Law and Economics
01 Department of Law and Economics > Volkswirtschaftliche Fachgebiete
Date Deposited: 07 Nov 2009 08:55
Official URL: http://econstor.eu/bitstream/10419/84842/1/ddpie_113.pdf
Additional Information:

JEL-Classification: C12, C22

Export:

Optionen (nur für Redakteure)

View Item View Item