GMM inference when the number of moment conditions is large

Roger Koenker, José A.F. Machado

Research output: Contribution to journalArticle

41 Citations (Scopus)

Abstract

Asymptotic theory typically presumes that the dimensionality of econometric models is independent of the sample size even though this presumption is often quite unrealistic. In GMM estimation, whenever optimal instruments are not available, it can frequently be shown that adding over-identifying restrictions (moment conditions) will increase asymptotic precision. However, the conventional asymptotics which underlies this view insists that the number of moment conditions remain finite even though the number of available moment conditions may grow without bound. We consider the explicit dependence of the number of moment conditions (or instruments), qn, on the sample size, n, and establish that, under conventional regularity conditions for the estimation of a linear model with general heteroskedasticity, q3 n/n → 0 is a sufficient condition for the validity of conventional asymptotic inference about the GMM estimator.

Original languageEnglish
Pages (from-to)327-344
Number of pages18
JournalJournal of Econometrics
Volume93
Issue number2
DOIs
Publication statusPublished - 1 Jan 1999

Fingerprint

Inference
Moment conditions
Sample size
Dimensionality
Optimal instruments
Asymptotic theory
GMM estimation
Econometric models
Heteroskedasticity
GMM estimator
Regularity

Keywords

  • Asymptotic expansion
  • GMM
  • Method of moments

Cite this

@article{e157c612d23147b293501473ee1503dc,
title = "GMM inference when the number of moment conditions is large",
abstract = "Asymptotic theory typically presumes that the dimensionality of econometric models is independent of the sample size even though this presumption is often quite unrealistic. In GMM estimation, whenever optimal instruments are not available, it can frequently be shown that adding over-identifying restrictions (moment conditions) will increase asymptotic precision. However, the conventional asymptotics which underlies this view insists that the number of moment conditions remain finite even though the number of available moment conditions may grow without bound. We consider the explicit dependence of the number of moment conditions (or instruments), qn, on the sample size, n, and establish that, under conventional regularity conditions for the estimation of a linear model with general heteroskedasticity, q3 n/n → 0 is a sufficient condition for the validity of conventional asymptotic inference about the GMM estimator.",
keywords = "Asymptotic expansion, GMM, Method of moments",
author = "Roger Koenker and Machado, {Jos{\'e} A.F.}",
year = "1999",
month = "1",
day = "1",
doi = "10.1016/S0304-4076(99)00014-7",
language = "English",
volume = "93",
pages = "327--344",
journal = "Journal of Econometrics",
issn = "0304-4076",
publisher = "Elsevier Science",
number = "2",

}

GMM inference when the number of moment conditions is large. / Koenker, Roger; Machado, José A.F.

In: Journal of Econometrics, Vol. 93, No. 2, 01.01.1999, p. 327-344.

Research output: Contribution to journalArticle

TY - JOUR

T1 - GMM inference when the number of moment conditions is large

AU - Koenker, Roger

AU - Machado, José A.F.

PY - 1999/1/1

Y1 - 1999/1/1

N2 - Asymptotic theory typically presumes that the dimensionality of econometric models is independent of the sample size even though this presumption is often quite unrealistic. In GMM estimation, whenever optimal instruments are not available, it can frequently be shown that adding over-identifying restrictions (moment conditions) will increase asymptotic precision. However, the conventional asymptotics which underlies this view insists that the number of moment conditions remain finite even though the number of available moment conditions may grow without bound. We consider the explicit dependence of the number of moment conditions (or instruments), qn, on the sample size, n, and establish that, under conventional regularity conditions for the estimation of a linear model with general heteroskedasticity, q3 n/n → 0 is a sufficient condition for the validity of conventional asymptotic inference about the GMM estimator.

AB - Asymptotic theory typically presumes that the dimensionality of econometric models is independent of the sample size even though this presumption is often quite unrealistic. In GMM estimation, whenever optimal instruments are not available, it can frequently be shown that adding over-identifying restrictions (moment conditions) will increase asymptotic precision. However, the conventional asymptotics which underlies this view insists that the number of moment conditions remain finite even though the number of available moment conditions may grow without bound. We consider the explicit dependence of the number of moment conditions (or instruments), qn, on the sample size, n, and establish that, under conventional regularity conditions for the estimation of a linear model with general heteroskedasticity, q3 n/n → 0 is a sufficient condition for the validity of conventional asymptotic inference about the GMM estimator.

KW - Asymptotic expansion

KW - GMM

KW - Method of moments

UR - http://www.scopus.com/inward/record.url?scp=0010666697&partnerID=8YFLogxK

U2 - 10.1016/S0304-4076(99)00014-7

DO - 10.1016/S0304-4076(99)00014-7

M3 - Article

VL - 93

SP - 327

EP - 344

JO - Journal of Econometrics

JF - Journal of Econometrics

SN - 0304-4076

IS - 2

ER -