A panel cointegrating rank test with structural breaks and cross-sectional dependence

Antonia Arsova; Deniz Dilan Karaman Örsal

doi:10.1016/j.ecosta.2020.05.002

A panel cointegrating rank test with structural breaks and cross-sectional dependence

Research output: Journal contributions › Journal articles › Research › peer-review

9 Citations (Scopus)

Abstract

A new panel cointegrating rank test which allows for a linear time trend with breaks and cross-sectional dependence is proposed. The new correlation-augmented inverse normal (CAIN) test is based on a modification of the inverse normal method and combines the p-values of individual likelihood-ratio trace statistics by assuming that the number of breaks and break points are known. A Monte Carlo study demonstrates its robustness to cross-sectional dependence and its superior size and power properties compared to other meta-analytic tests used in practice. The test is applied to investigate the long-run relationship between regional house prices and personal income in the United States in view of the structural break introduced by the Global Financial Crisis.

Original language	English
Journal	Econometrics and Statistics
Volume	17
Pages (from-to)	107-129
Number of pages	23
ISSN	2452-3062
DOIs	https://doi.org/10.1016/j.ecosta.2020.05.002
Publication status	Published - 01.01.2021

Bibliographical note

Funding Information:
Financial support by the German Research Foundation (DFG) through the project KA-3145/1-2 is gratefully acknowledged. The authors also thank two anonymous referees and the associate editor for many helpful comments and suggestions.

Publisher Copyright:
© 2020 The Author(s)

Research areas and keywords

Economics
Panel cointegrating rank test
Structural breaks
Cross-sectional dependence
likelihood-ratio
Time trend

ASJC Scopus Subject Areas

Statistics, Probability and Uncertainty
Economics and Econometrics
Statistics and Probability

Access to Document

10.1016/j.ecosta.2020.05.002Licence: CC BY-NC-ND

DownloadFinal published version, 969 KBLicence: CC BY-NC-ND

Cite this

@article{177a6a2c77c745eabf9603a784593793,

title = "A panel cointegrating rank test with structural breaks and cross-sectional dependence",

abstract = "A new panel cointegrating rank test which allows for a linear time trend with breaks and cross-sectional dependence is proposed. The new correlation-augmented inverse normal (CAIN) test is based on a modification of the inverse normal method and combines the p-values of individual likelihood-ratio trace statistics by assuming that the number of breaks and break points are known. A Monte Carlo study demonstrates its robustness to cross-sectional dependence and its superior size and power properties compared to other meta-analytic tests used in practice. The test is applied to investigate the long-run relationship between regional house prices and personal income in the United States in view of the structural break introduced by the Global Financial Crisis.",

keywords = "Economics, Panel cointegrating rank test, Structural breaks, Cross-sectional dependence, likelihood-ratio, Time trend",

author = "Antonia Arsova and \{Karaman {\"O}rsal\}, \{Deniz Dilan\}",

note = "Funding Information: Financial support by the German Research Foundation (DFG) through the project KA-3145/1-2 is gratefully acknowledged. The authors also thank two anonymous referees and the associate editor for many helpful comments and suggestions. Publisher Copyright: {\textcopyright} 2020 The Author(s)",

year = "2021",

month = jan,

day = "1",

doi = "10.1016/j.ecosta.2020.05.002",

language = "English",

volume = "17",

pages = "107--129",

journal = "Econometrics and Statistics",

issn = "2452-3062",

publisher = "Elsevier Bedrijfsinformatie bv",

}

TY - JOUR

T1 - A panel cointegrating rank test with structural breaks and cross-sectional dependence

AU - Arsova, Antonia

AU - Karaman Örsal, Deniz Dilan

N1 - Funding Information: Financial support by the German Research Foundation (DFG) through the project KA-3145/1-2 is gratefully acknowledged. The authors also thank two anonymous referees and the associate editor for many helpful comments and suggestions. Publisher Copyright: © 2020 The Author(s)

PY - 2021/1/1

Y1 - 2021/1/1

N2 - A new panel cointegrating rank test which allows for a linear time trend with breaks and cross-sectional dependence is proposed. The new correlation-augmented inverse normal (CAIN) test is based on a modification of the inverse normal method and combines the p-values of individual likelihood-ratio trace statistics by assuming that the number of breaks and break points are known. A Monte Carlo study demonstrates its robustness to cross-sectional dependence and its superior size and power properties compared to other meta-analytic tests used in practice. The test is applied to investigate the long-run relationship between regional house prices and personal income in the United States in view of the structural break introduced by the Global Financial Crisis.

AB - A new panel cointegrating rank test which allows for a linear time trend with breaks and cross-sectional dependence is proposed. The new correlation-augmented inverse normal (CAIN) test is based on a modification of the inverse normal method and combines the p-values of individual likelihood-ratio trace statistics by assuming that the number of breaks and break points are known. A Monte Carlo study demonstrates its robustness to cross-sectional dependence and its superior size and power properties compared to other meta-analytic tests used in practice. The test is applied to investigate the long-run relationship between regional house prices and personal income in the United States in view of the structural break introduced by the Global Financial Crisis.

KW - Economics

KW - Panel cointegrating rank test

KW - Structural breaks

KW - Cross-sectional dependence

KW - likelihood-ratio

KW - Time trend

UR - https://www.scopus.com/pages/publications/85087934240

UR - https://www.mendeley.com/catalogue/8ad8bf7e-8978-3698-9995-6f498248fa17/

U2 - 10.1016/j.ecosta.2020.05.002

DO - 10.1016/j.ecosta.2020.05.002

M3 - Journal articles

SN - 2452-3062

VL - 17

SP - 107

EP - 129

JO - Econometrics and Statistics

JF - Econometrics and Statistics

ER -

A panel cointegrating rank test with structural breaks and cross-sectional dependence

Abstract

Bibliographical note

Research areas and keywords

ASJC Scopus Subject Areas

Access to Document

Fingerprint

Cite this