Efficiency gains of system GMM and MDE over individual equation estimation

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

In the econometric literature it is known that, under certain conditions, estimating a system of equations together is more efficient than estimating each equation separately. This finding has been proved, however, only under the assumption of a known parametric form of heteroskedasticity (including homoskedasticity) or non-random regressors/instruments. This note shows that an analogous finding holds for GMM under heteroskedasticity of unknown form and random regressors/instruments. Specifically, I provide a necessary condition for the efficiency gain of the system GMM over the single-equation GMM. An analogous necessary condition for the efficiency gain is also shown to hold for minimum-distance (or X2) estimation (MDE).

Original languageEnglish
Pages (from-to)451-459
Number of pages9
JournalJapanese Economic Review
Volume55
Issue number4
Publication statusPublished - 2004 Dec 1
Externally publishedYes

Fingerprint

Efficiency gains
Heteroskedasticity
System-GMM
Econometrics
Minimum distance

ASJC Scopus subject areas

  • Economics and Econometrics

Cite this

Efficiency gains of system GMM and MDE over individual equation estimation. / Lee, Myoung-jae.

In: Japanese Economic Review, Vol. 55, No. 4, 01.12.2004, p. 451-459.

Research output: Contribution to journalArticle

@article{716463c3591340cd84ecccdd9a6d203b,
title = "Efficiency gains of system GMM and MDE over individual equation estimation",
abstract = "In the econometric literature it is known that, under certain conditions, estimating a system of equations together is more efficient than estimating each equation separately. This finding has been proved, however, only under the assumption of a known parametric form of heteroskedasticity (including homoskedasticity) or non-random regressors/instruments. This note shows that an analogous finding holds for GMM under heteroskedasticity of unknown form and random regressors/instruments. Specifically, I provide a necessary condition for the efficiency gain of the system GMM over the single-equation GMM. An analogous necessary condition for the efficiency gain is also shown to hold for minimum-distance (or X2) estimation (MDE).",
author = "Myoung-jae Lee",
year = "2004",
month = "12",
day = "1",
language = "English",
volume = "55",
pages = "451--459",
journal = "Japanese Economic Review",
issn = "1352-4739",
publisher = "Wiley-Blackwell",
number = "4",

}

TY - JOUR

T1 - Efficiency gains of system GMM and MDE over individual equation estimation

AU - Lee, Myoung-jae

PY - 2004/12/1

Y1 - 2004/12/1

N2 - In the econometric literature it is known that, under certain conditions, estimating a system of equations together is more efficient than estimating each equation separately. This finding has been proved, however, only under the assumption of a known parametric form of heteroskedasticity (including homoskedasticity) or non-random regressors/instruments. This note shows that an analogous finding holds for GMM under heteroskedasticity of unknown form and random regressors/instruments. Specifically, I provide a necessary condition for the efficiency gain of the system GMM over the single-equation GMM. An analogous necessary condition for the efficiency gain is also shown to hold for minimum-distance (or X2) estimation (MDE).

AB - In the econometric literature it is known that, under certain conditions, estimating a system of equations together is more efficient than estimating each equation separately. This finding has been proved, however, only under the assumption of a known parametric form of heteroskedasticity (including homoskedasticity) or non-random regressors/instruments. This note shows that an analogous finding holds for GMM under heteroskedasticity of unknown form and random regressors/instruments. Specifically, I provide a necessary condition for the efficiency gain of the system GMM over the single-equation GMM. An analogous necessary condition for the efficiency gain is also shown to hold for minimum-distance (or X2) estimation (MDE).

UR - http://www.scopus.com/inward/record.url?scp=11244253850&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=11244253850&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:11244253850

VL - 55

SP - 451

EP - 459

JO - Japanese Economic Review

JF - Japanese Economic Review

SN - 1352-4739

IS - 4

ER -