Bootstrap tests for overidentification in linear regression models

Russell Davidson and James MacKinnon

No 274643, Queen's Economics Department Working Papers from Queen's University - Department of Economics

Abstract: Little attention has been paid to the nite-sample properties of tests for overidentifying restrictions in linear regression models with a single endogenous regressor and weak instruments. We study several such tests in models estimated by instrumental variables (IV) and limited-information maximum likelihood (LIML). Under the assumption of Gaussian disturbances, we derive expressions for a variety of test statistics as functions of eight mutually independent random variables and two nuisance parameters. The distributions of the statistics are shown to have an ill-dened limit as the parameter that determines the strength of the instruments tends to zero and as the correlation between the disturbances of the structural and reduced-form equations tends to plus or minus one. Simulation experiments demonstrate that this makes it impossible to perform reliable inference near the point at which the limit is ill-dened. Several bootstrap procedures are proposed. They alleviate the problem and allow reliable inference when the instruments are not too weak. We also study the power properties of the bootstrap tests.

Keywords: Financial; Economics (search for similar items in EconPapers)
Pages: 42
Date: 2014-04
References: Add references at CitEc
Citations:

Downloads: (external link)
https://ageconsearch.umn.edu/record/274643/files/qed_wp_1318.pdf (application/pdf)

Related works:
Journal Article: Bootstrap Tests for Overidentification in Linear Regression Models (2015)
Working Paper: Bootstrap Tests for Overidentification in Linear Regression Models (2015)
Working Paper: Bootstrap Tests For Overidentification In Linear Regression Models (2014)
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ags:quedwp:274643

DOI: 10.22004/ag.econ.274643

Access Statistics for this paper

More papers in Queen's Economics Department Working Papers from Queen's University - Department of Economics Contact information at EDIRC.
Bibliographic data for series maintained by AgEcon Search ().