Tests for seasonal unit roots in panels of cross-sectionally correlated time series

Dong Wan Shin; Man Suk Oh

doi:10.1080/02331880701600463

Tests for seasonal unit roots in panels of cross-sectionally correlated time series

Dong Wan Shin, Man Suk Oh

Department of Statistics

Research output: Contribution to journal › Article › peer-review

1 Scopus citations

Abstract

For panel models of cross-sectionally correlated time series, seasonal unit root tests are constructed for each seasonal frequency. The tests are based on instrumental variable estimators which are modifications of signs of the regressors. Cross-sectional correlation is controlled by rotating the system of time series using an estimated error covariance matrix. The limiting null distributions of the tests are chi-squared and are free from nuisance parameters arising from cross-sectional correlation. A Monte-Carlo experiment compares size and power performances of the proposed tests.

Original language	English
Pages (from-to)	139-152
Number of pages	14
Journal	Statistics
Volume	43
Issue number	2
DOIs	https://doi.org/10.1080/02331880701600463
State	Published - Apr 2009

Bibliographical note

Funding Information:
The authors are very grateful for the two anonymous referees for their comments. This work was supported by the Korea Research Foundation Grant funded by the Korean Government (MOEHRD) (KRF-2005-070-C00021).

Keywords

HEGY model
Instrumental variable estimation
Sign instrument

Access to Document

10.1080/02331880701600463

Cite this

@article{4e1988dbb118434894e501bc74035aaa,

title = "Tests for seasonal unit roots in panels of cross-sectionally correlated time series",

abstract = "For panel models of cross-sectionally correlated time series, seasonal unit root tests are constructed for each seasonal frequency. The tests are based on instrumental variable estimators which are modifications of signs of the regressors. Cross-sectional correlation is controlled by rotating the system of time series using an estimated error covariance matrix. The limiting null distributions of the tests are chi-squared and are free from nuisance parameters arising from cross-sectional correlation. A Monte-Carlo experiment compares size and power performances of the proposed tests.",

keywords = "HEGY model, Instrumental variable estimation, Sign instrument",

author = "Shin, {Dong Wan} and Oh, {Man Suk}",

note = "Funding Information: The authors are very grateful for the two anonymous referees for their comments. This work was supported by the Korea Research Foundation Grant funded by the Korean Government (MOEHRD) (KRF-2005-070-C00021).",

year = "2009",

month = apr,

doi = "10.1080/02331880701600463",

language = "English",

volume = "43",

pages = "139--152",

journal = "Statistics",

issn = "0233-1888",

publisher = "Taylor and Francis Ltd.",

number = "2",

}

TY - JOUR

T1 - Tests for seasonal unit roots in panels of cross-sectionally correlated time series

AU - Shin, Dong Wan

AU - Oh, Man Suk

N1 - Funding Information: The authors are very grateful for the two anonymous referees for their comments. This work was supported by the Korea Research Foundation Grant funded by the Korean Government (MOEHRD) (KRF-2005-070-C00021).

PY - 2009/4

Y1 - 2009/4

N2 - For panel models of cross-sectionally correlated time series, seasonal unit root tests are constructed for each seasonal frequency. The tests are based on instrumental variable estimators which are modifications of signs of the regressors. Cross-sectional correlation is controlled by rotating the system of time series using an estimated error covariance matrix. The limiting null distributions of the tests are chi-squared and are free from nuisance parameters arising from cross-sectional correlation. A Monte-Carlo experiment compares size and power performances of the proposed tests.

AB - For panel models of cross-sectionally correlated time series, seasonal unit root tests are constructed for each seasonal frequency. The tests are based on instrumental variable estimators which are modifications of signs of the regressors. Cross-sectional correlation is controlled by rotating the system of time series using an estimated error covariance matrix. The limiting null distributions of the tests are chi-squared and are free from nuisance parameters arising from cross-sectional correlation. A Monte-Carlo experiment compares size and power performances of the proposed tests.

KW - HEGY model

KW - Instrumental variable estimation

KW - Sign instrument

UR - http://www.scopus.com/inward/record.url?scp=69249211231&partnerID=8YFLogxK

U2 - 10.1080/02331880701600463

DO - 10.1080/02331880701600463

M3 - Article

AN - SCOPUS:69249211231

SN - 0233-1888

VL - 43

SP - 139

EP - 152

JO - Statistics

JF - Statistics

IS - 2

ER -

Tests for seasonal unit roots in panels of cross-sectionally correlated time series

Abstract

Bibliographical note

Keywords

Access to Document

Fingerprint

Cite this