Likelihood-based panel cointegration test in the presence of a linear time trend and cross-sectional dependence

Research output: Working paperWorking papers

Standard

Likelihood-based panel cointegration test in the presence of a linear time trend and cross-sectional dependence. / Arsova, Antonia; Karaman Örsal, Deniz.
Lüneburg: Institut für Volkswirtschaftslehre der Universität Lüneburg, 2013. (Working Paper Series; No. 280).

Research output: Working paperWorking papers

Harvard

Arsova, A & Karaman Örsal, D 2013 'Likelihood-based panel cointegration test in the presence of a linear time trend and cross-sectional dependence' Working Paper Series, no. 280, Institut für Volkswirtschaftslehre der Universität Lüneburg, Lüneburg.

APA

Arsova, A., & Karaman Örsal, D. (2013). Likelihood-based panel cointegration test in the presence of a linear time trend and cross-sectional dependence. (Working Paper Series; No. 280). Institut für Volkswirtschaftslehre der Universität Lüneburg.

Vancouver

Arsova A, Karaman Örsal D. Likelihood-based panel cointegration test in the presence of a linear time trend and cross-sectional dependence. Lüneburg: Institut für Volkswirtschaftslehre der Universität Lüneburg. 2013 Aug. (Working Paper Series; 280).

Bibtex

@techreport{6bc6dd58ec3344bfaedccffa6b36dc06,
title = "Likelihood-based panel cointegration test in the presence of a linear time trend and cross-sectional dependence",
abstract = "This paper proposes a new likelihood-based panel cointegration rank test which extends the test of {\"O}rsal & Droge (2012) (henceforth Panel SL test) to allow for cross-sectional dependence. The dependence is modelled by unobserved common factors which affect the variables in each cross-section through heterogeneous loadings. The common components are estimated following the panel analysis of nonstationarity in idiosyncratic and common components (PANIC) approach of Bai & Ng (2004) and the estimates are subtracted from the observations. The cointegrating rank of the defactored data is then tested by the Panel SL test. A Monte Carlo study demonstrates that the proposed testing procedure has reasonable size and power properties in finite samples.",
keywords = "Economics, empirical/statistics, panel cointegration rank test, cross-sectional dependence, common factors, likelihood-ratio, time trend",
author = "Antonia Arsova and {Karaman {\"O}rsal}, Deniz",
year = "2013",
month = aug,
language = "English",
series = "Working Paper Series",
publisher = "Institut f{\"u}r Volkswirtschaftslehre der Universit{\"a}t L{\"u}neburg",
number = "280",
type = "WorkingPaper",
institution = "Institut f{\"u}r Volkswirtschaftslehre der Universit{\"a}t L{\"u}neburg",

}

RIS

TY - UNPB

T1 - Likelihood-based panel cointegration test in the presence of a linear time trend and cross-sectional dependence

AU - Arsova, Antonia

AU - Karaman Örsal, Deniz

PY - 2013/8

Y1 - 2013/8

N2 - This paper proposes a new likelihood-based panel cointegration rank test which extends the test of Örsal & Droge (2012) (henceforth Panel SL test) to allow for cross-sectional dependence. The dependence is modelled by unobserved common factors which affect the variables in each cross-section through heterogeneous loadings. The common components are estimated following the panel analysis of nonstationarity in idiosyncratic and common components (PANIC) approach of Bai & Ng (2004) and the estimates are subtracted from the observations. The cointegrating rank of the defactored data is then tested by the Panel SL test. A Monte Carlo study demonstrates that the proposed testing procedure has reasonable size and power properties in finite samples.

AB - This paper proposes a new likelihood-based panel cointegration rank test which extends the test of Örsal & Droge (2012) (henceforth Panel SL test) to allow for cross-sectional dependence. The dependence is modelled by unobserved common factors which affect the variables in each cross-section through heterogeneous loadings. The common components are estimated following the panel analysis of nonstationarity in idiosyncratic and common components (PANIC) approach of Bai & Ng (2004) and the estimates are subtracted from the observations. The cointegrating rank of the defactored data is then tested by the Panel SL test. A Monte Carlo study demonstrates that the proposed testing procedure has reasonable size and power properties in finite samples.

KW - Economics, empirical/statistics

KW - panel cointegration rank test

KW - cross-sectional dependence

KW - common factors

KW - likelihood-ratio

KW - time trend

M3 - Working papers

T3 - Working Paper Series

BT - Likelihood-based panel cointegration test in the presence of a linear time trend and cross-sectional dependence

PB - Institut für Volkswirtschaftslehre der Universität Lüneburg

CY - Lüneburg

ER -

Documents