Validity of Subsampling and 'Plug-In Asymptotic' Inference for Parameters Defined by Moment Inequalities

44 Pages Posted: 5 Aug 2007

See all articles by Donald W. K. Andrews

Donald W. K. Andrews

Yale University - Cowles Foundation

Patrik Guggenberger

Pennsylvania State University, College of the Liberal Arts - Department of Economic

Date Written: July 2007

Abstract

This paper considers inference for parameters defined by moment inequalities and equalities. The parameters need not be identified. For a specified class of test statistics, this paper establishes the uniform asymptotic validity of subsampling, m out of n bootstrap, and plug-in asymptotic tests and confidence intervals for such parameters. Establishing uniform asymptotic validity is crucial in moment inequality problems because the test statistics of interest have discontinuities in their pointwise asymptotic distributions.

The size results are quite general because they hold without specifying the particular form of the moment conditions - only 2+delta moments finite are required. The results allow for i.i.d. and dependent observations and for preliminary consistent estimation of identified parameters.

Keywords: Asymptotic size, Confidence set, Exact size, m out of n bootstrap, Subsampling, Moment inequalities

JEL Classification: C12, C15

Suggested Citation

Andrews, Donald W. K. and Guggenberger, Patrik, Validity of Subsampling and 'Plug-In Asymptotic' Inference for Parameters Defined by Moment Inequalities (July 2007). Cowles Foundation Discussion Paper No. 1620, Available at SSRN: https://ssrn.com/abstract=1003798

Donald W. K. Andrews (Contact Author)

Yale University - Cowles Foundation ( email )

Box 208281
New Haven, CT 06520-8281
United States
203-432-3698 (Phone)
203-432-6167 (Fax)

Patrik Guggenberger

Pennsylvania State University, College of the Liberal Arts - Department of Economic ( email )

524 Kern Graduate Building
University Park, PA 16802-3306
United States