Asymptotic efficiency in parametric structural models with parameter-dependent support

Keisuke Hirano, Jack R. Porter

Research output: Contribution to journalArticle

37 Citations (Scopus)

Abstract

In certain auction, search, and related models, the boundary of the support of the observed data depends on some of the parameters of interest. For such nonregular models, standard asymptotic distribution theory does not apply. Previous work has focused on characterizing the nonstandard limiting distributions of particular estimators in these models. In contrast, we study the problem of constructing efficient point estimators. We show that the maximum likelihood estimator is generally inefficient, but that the Bayes estimator is efficient according to the local asymptotic minmax criterion for conventional loss functions. We provide intuition for this result using Le Cam's limits of experiments framework.

Original languageEnglish (US)
Pages (from-to)1307-1338
Number of pages32
JournalEconometrica
Volume71
Issue number5
StatePublished - 2003
Externally publishedYes

Fingerprint

Asymptotic Efficiency
Structural Model
Parametric Model
structural model
Estimator
Efficient Points
efficiency
Bayes Estimator
Distribution Theory
Dependent
Asymptotic Theory
Auctions
Loss Function
Min-max
distribution theory
Limiting Distribution
Maximum Likelihood Estimator
Asymptotic distribution
Standard Model
auction

Keywords

  • Efficiency bounds
  • Limits of experiments
  • Local asymptotic minmax
  • Nonregular models
  • Parameter-dependent support

ASJC Scopus subject areas

  • Mathematics (miscellaneous)
  • Statistics and Probability
  • Economics and Econometrics
  • Social Sciences (miscellaneous)

Cite this

Asymptotic efficiency in parametric structural models with parameter-dependent support. / Hirano, Keisuke; Porter, Jack R.

In: Econometrica, Vol. 71, No. 5, 2003, p. 1307-1338.

Research output: Contribution to journalArticle

@article{3247d6f6d9c94852af27c50e41a6e69b,
title = "Asymptotic efficiency in parametric structural models with parameter-dependent support",
abstract = "In certain auction, search, and related models, the boundary of the support of the observed data depends on some of the parameters of interest. For such nonregular models, standard asymptotic distribution theory does not apply. Previous work has focused on characterizing the nonstandard limiting distributions of particular estimators in these models. In contrast, we study the problem of constructing efficient point estimators. We show that the maximum likelihood estimator is generally inefficient, but that the Bayes estimator is efficient according to the local asymptotic minmax criterion for conventional loss functions. We provide intuition for this result using Le Cam's limits of experiments framework.",
keywords = "Efficiency bounds, Limits of experiments, Local asymptotic minmax, Nonregular models, Parameter-dependent support",
author = "Keisuke Hirano and Porter, {Jack R.}",
year = "2003",
language = "English (US)",
volume = "71",
pages = "1307--1338",
journal = "Econometrica",
issn = "0012-9682",
publisher = "Wiley-Blackwell",
number = "5",

}

TY - JOUR

T1 - Asymptotic efficiency in parametric structural models with parameter-dependent support

AU - Hirano, Keisuke

AU - Porter, Jack R.

PY - 2003

Y1 - 2003

N2 - In certain auction, search, and related models, the boundary of the support of the observed data depends on some of the parameters of interest. For such nonregular models, standard asymptotic distribution theory does not apply. Previous work has focused on characterizing the nonstandard limiting distributions of particular estimators in these models. In contrast, we study the problem of constructing efficient point estimators. We show that the maximum likelihood estimator is generally inefficient, but that the Bayes estimator is efficient according to the local asymptotic minmax criterion for conventional loss functions. We provide intuition for this result using Le Cam's limits of experiments framework.

AB - In certain auction, search, and related models, the boundary of the support of the observed data depends on some of the parameters of interest. For such nonregular models, standard asymptotic distribution theory does not apply. Previous work has focused on characterizing the nonstandard limiting distributions of particular estimators in these models. In contrast, we study the problem of constructing efficient point estimators. We show that the maximum likelihood estimator is generally inefficient, but that the Bayes estimator is efficient according to the local asymptotic minmax criterion for conventional loss functions. We provide intuition for this result using Le Cam's limits of experiments framework.

KW - Efficiency bounds

KW - Limits of experiments

KW - Local asymptotic minmax

KW - Nonregular models

KW - Parameter-dependent support

UR - http://www.scopus.com/inward/record.url?scp=0142007875&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0142007875&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0142007875

VL - 71

SP - 1307

EP - 1338

JO - Econometrica

JF - Econometrica

SN - 0012-9682

IS - 5

ER -