Efficiency comparison of random effects two stage least squares estimators

Chirok Han

doi:10.1016/j.econlet.2016.09.007

Efficiency comparison of random effects two stage least squares estimators

Chirok Han

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

5 Citations (Scopus)

Abstract

For two stage least squares estimation (2SLS) with panel data, Baltagi and Li (1992) have shown that Baltagi's (1981) error-component 2SLS and Balestra and Varadharajan-Krishnakumar's (1987) generalized 2SLS are equivalent in terms of asymptotic variance under the random effects error-component assumption. In the present paper this asymptotic equivalence is extended to models with heteroskedastic and serial correlated errors. However, it is shown that the equivalence does not hold if fixed effects are present in the reduced-form equations. The theoretical claims are verified by simulations and are examined for Cornwell and Trumbull's (1994) model and data.

Original language	English
Pages (from-to)	59-62
Number of pages	4
Journal	Economics Letters
Volume	148
DOIs	https://doi.org/10.1016/j.econlet.2016.09.007
Publication status	Published - 2016 Nov 1

Bibliographical note

Funding Information:
The author thanks Professor Badi H. Baltagi and an anonymous referee for comments. This research was financially supported by the Korean Government ( NRF-2014S1A2A2027803 ) and partly by Korea University ( K1510291 ).

Publisher Copyright:
© 2016 Elsevier B.V.

Copyright:
Copyright 2016 Elsevier B.V., All rights reserved.

Keywords

EC2SLS
Efficiency
G2SLS
Panel data
Random effects
Two stage least squares

ASJC Scopus subject areas

Finance
Economics and Econometrics

Access to Document

10.1016/j.econlet.2016.09.007

Cite this

@article{f4f1cd9d983746b2be31ab0bcaee1eb4,

title = "Efficiency comparison of random effects two stage least squares estimators",

abstract = "For two stage least squares estimation (2SLS) with panel data, Baltagi and Li (1992) have shown that Baltagi's (1981) error-component 2SLS and Balestra and Varadharajan-Krishnakumar's (1987) generalized 2SLS are equivalent in terms of asymptotic variance under the random effects error-component assumption. In the present paper this asymptotic equivalence is extended to models with heteroskedastic and serial correlated errors. However, it is shown that the equivalence does not hold if fixed effects are present in the reduced-form equations. The theoretical claims are verified by simulations and are examined for Cornwell and Trumbull's (1994) model and data.",

keywords = "EC2SLS, Efficiency, G2SLS, Panel data, Random effects, Two stage least squares",

author = "Chirok Han",

note = "Funding Information: The author thanks Professor Badi H. Baltagi and an anonymous referee for comments. This research was financially supported by the Korean Government ( NRF-2014S1A2A2027803 ) and partly by Korea University ( K1510291 ). Publisher Copyright: {\textcopyright} 2016 Elsevier B.V. Copyright: Copyright 2016 Elsevier B.V., All rights reserved.",

year = "2016",

month = nov,

day = "1",

doi = "10.1016/j.econlet.2016.09.007",

language = "English",

volume = "148",

pages = "59--62",

journal = "Economics Letters",

issn = "0165-1765",

publisher = "Elsevier",

}

TY - JOUR

T1 - Efficiency comparison of random effects two stage least squares estimators

AU - Han, Chirok

N1 - Funding Information: The author thanks Professor Badi H. Baltagi and an anonymous referee for comments. This research was financially supported by the Korean Government ( NRF-2014S1A2A2027803 ) and partly by Korea University ( K1510291 ). Publisher Copyright: © 2016 Elsevier B.V. Copyright: Copyright 2016 Elsevier B.V., All rights reserved.

PY - 2016/11/1

Y1 - 2016/11/1

N2 - For two stage least squares estimation (2SLS) with panel data, Baltagi and Li (1992) have shown that Baltagi's (1981) error-component 2SLS and Balestra and Varadharajan-Krishnakumar's (1987) generalized 2SLS are equivalent in terms of asymptotic variance under the random effects error-component assumption. In the present paper this asymptotic equivalence is extended to models with heteroskedastic and serial correlated errors. However, it is shown that the equivalence does not hold if fixed effects are present in the reduced-form equations. The theoretical claims are verified by simulations and are examined for Cornwell and Trumbull's (1994) model and data.

AB - For two stage least squares estimation (2SLS) with panel data, Baltagi and Li (1992) have shown that Baltagi's (1981) error-component 2SLS and Balestra and Varadharajan-Krishnakumar's (1987) generalized 2SLS are equivalent in terms of asymptotic variance under the random effects error-component assumption. In the present paper this asymptotic equivalence is extended to models with heteroskedastic and serial correlated errors. However, it is shown that the equivalence does not hold if fixed effects are present in the reduced-form equations. The theoretical claims are verified by simulations and are examined for Cornwell and Trumbull's (1994) model and data.

KW - EC2SLS

KW - Efficiency

KW - G2SLS

KW - Panel data

KW - Random effects

KW - Two stage least squares

UR - http://www.scopus.com/inward/record.url?scp=84989165799&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84989165799&partnerID=8YFLogxK

U2 - 10.1016/j.econlet.2016.09.007

DO - 10.1016/j.econlet.2016.09.007

M3 - Article

AN - SCOPUS:84989165799

SN - 0165-1765

VL - 148

SP - 59

EP - 62

JO - Economics Letters

JF - Economics Letters

ER -

Efficiency comparison of random effects two stage least squares estimators

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this