Invalidity of the Bootstrap and the m Out of n Bootstrap for Interval Endpoints Defined by Moment Inequalities
36 Pages Posted: 28 Jul 2008 Last revised: 19 Aug 2008
Date Written: July 28, 2008
Abstract
This paper analyzes the finite-sample and asymptotic properties of several bootstrap and m out of n bootstrap methods for constructing confidence interval (CI) endpoints in models defined by moment inequalities. In particular, we consider using these methods directly to construct CI endpoints. By considering two very simple models, the paper shows that neither the bootstrap nor the m out of n bootstrap is valid in finite samples or in a uniform asymptotic sense in general when applied directly to construct CI endpoints.
In contrast, other results in the literature show that other ways of applying the bootstrap, m out of n bootstrap, and subsampling do lead to uniformly asymptotically valid confidence sets in moment inequality models. Thus, the uniform asymptotic validity of resampling methods in moment inequality models depends on the way in which the resampling methods are employed.
Keywords: Bootstrap, Coverage probability, m out of n bootstrap, Moment inequality model, Partial identification, Subsampling
JEL Classification: C01
Suggested Citation: Suggested Citation
Do you have a job opening that you would like to promote on SSRN?
Recommended Papers
-
Inference in Incomplete Models
By Alfred Galichon and Marc Henry
-
Asymptotic Properties for a Class of Partially Identified Models
-
Inference for Parameters Defined by Moment Inequalities Using Generalized Moment Selection
-
Applications of Subsampling, Hybrid, and Size-Correction Methods
-
Set Identification in Models with Multiple Equilibria
By Alfred Galichon and Marc Henry
-
The Limit of Finite-Sample Size and a Problem With Subsampling
-
Bayesian and Frequentist Inference in Partially Identified Models
-
A Test of Non-Identifying Restrictions and Confidence Regions for Partially Identified Parameters
By Alfred Galichon and Marc Henry