Which moments to match?

Andrew Ronald Gallant, George Tauchen

Research output: Contribution to journalArticle

426 Citations (Scopus)

Abstract

We describe an intuitive, simple, and systematic approach to generating moment conditions for generalized method of moments (GMM) estimation of the parameters of a structural model. The idea is to use the score of a density that has an analytic expression to define the GMM criterion. The auxiliary model that generates the score should closely approximate the distribution of the observed data, but is not required to nest it. If the auxiliary model nests the structural model then the estimator is as efficient as maximum likelihood. The estimator is advantageous when expectations under a structural model can be computed by simulation, by quadrature, or by analytic expressions but the likelihood cannot be computed easily.

Original languageEnglish (US)
Pages (from-to)657-681
Number of pages25
JournalEconometric Theory
Volume12
Issue number4
StatePublished - 1996

Fingerprint

structural model
simulation
Structural model
Generalized method of moments
Estimator

All Science Journal Classification (ASJC) codes

  • Economics and Econometrics
  • Social Sciences (miscellaneous)

Cite this

Gallant, A. R., & Tauchen, G. (1996). Which moments to match? Econometric Theory, 12(4), 657-681.
Gallant, Andrew Ronald ; Tauchen, George. / Which moments to match?. In: Econometric Theory. 1996 ; Vol. 12, No. 4. pp. 657-681.
@article{1d64c07bd0804c0883ed9ede29bec888,
title = "Which moments to match?",
abstract = "We describe an intuitive, simple, and systematic approach to generating moment conditions for generalized method of moments (GMM) estimation of the parameters of a structural model. The idea is to use the score of a density that has an analytic expression to define the GMM criterion. The auxiliary model that generates the score should closely approximate the distribution of the observed data, but is not required to nest it. If the auxiliary model nests the structural model then the estimator is as efficient as maximum likelihood. The estimator is advantageous when expectations under a structural model can be computed by simulation, by quadrature, or by analytic expressions but the likelihood cannot be computed easily.",
author = "Gallant, {Andrew Ronald} and George Tauchen",
year = "1996",
language = "English (US)",
volume = "12",
pages = "657--681",
journal = "Econometric Theory",
issn = "0266-4666",
publisher = "Cambridge University Press",
number = "4",

}

Gallant, AR & Tauchen, G 1996, 'Which moments to match?', Econometric Theory, vol. 12, no. 4, pp. 657-681.

Which moments to match? / Gallant, Andrew Ronald; Tauchen, George.

In: Econometric Theory, Vol. 12, No. 4, 1996, p. 657-681.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Which moments to match?

AU - Gallant, Andrew Ronald

AU - Tauchen, George

PY - 1996

Y1 - 1996

N2 - We describe an intuitive, simple, and systematic approach to generating moment conditions for generalized method of moments (GMM) estimation of the parameters of a structural model. The idea is to use the score of a density that has an analytic expression to define the GMM criterion. The auxiliary model that generates the score should closely approximate the distribution of the observed data, but is not required to nest it. If the auxiliary model nests the structural model then the estimator is as efficient as maximum likelihood. The estimator is advantageous when expectations under a structural model can be computed by simulation, by quadrature, or by analytic expressions but the likelihood cannot be computed easily.

AB - We describe an intuitive, simple, and systematic approach to generating moment conditions for generalized method of moments (GMM) estimation of the parameters of a structural model. The idea is to use the score of a density that has an analytic expression to define the GMM criterion. The auxiliary model that generates the score should closely approximate the distribution of the observed data, but is not required to nest it. If the auxiliary model nests the structural model then the estimator is as efficient as maximum likelihood. The estimator is advantageous when expectations under a structural model can be computed by simulation, by quadrature, or by analytic expressions but the likelihood cannot be computed easily.

UR - http://www.scopus.com/inward/record.url?scp=18544376108&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=18544376108&partnerID=8YFLogxK

M3 - Article

VL - 12

SP - 657

EP - 681

JO - Econometric Theory

JF - Econometric Theory

SN - 0266-4666

IS - 4

ER -

Gallant AR, Tauchen G. Which moments to match? Econometric Theory. 1996;12(4):657-681.