Underidentification?

被引：19

作者：

Arellano, Manuel ^{[1
]}

Hansen, Lars Peter ^{[2
]}

Sentana, Enrique ^{[1
]}

机构：

[1] CEMFI, E-28014 Madrid, Spain

[2] Univ Chicago, Dept Econ, Chicago, IL 60637 USA

来源：

JOURNAL OF ECONOMETRICS | 2012年 / 170卷 / 02期

基金：

美国国家科学基金会;

关键词：

GENERALIZED-METHOD; SAMPLE PROPERTIES; IDENTIFICATION; GMM; SPECIFICATION; ESTIMATORS; MODELS; TESTS;

D O I：

10.1016/j.jeconom.2012.05.005

中图分类号：

F [经济];

学科分类号：

02 ;

摘要：

We develop methods for testing that an econometric model is underidentified and for estimating the nature of the failed identification. We adopt a generalized-method-of moments perspective in a possibly non-linear econometric specification. If, after attempting to replicate the structural relation, we find substantial evidence against the overidentifying restrictions of an augmented model, this is evidence against underidentification of the original model. To diagnose how identification might fail, we study the estimation of a one-dimensional curve that gives the parameter configurations that provide the greatest challenge to identification, and we illustrate this calculation in an empirical example. (c) 2012 Elsevier B.V. All rights reserved.

引用

页码：256 / 280

页数：25

共 49 条

[11] Estimation and confidence regions for parameter sets in econometric models [J].