Andrews gratefully acknowledges the research support of the National Science Foundation via Grants SES-0751517 and SES-1058376. The authors thank Steve Berry for numerous discussions and comments. The authors also thank a co-editor, three referees, Michael Wolf, and Giovanni Compiani for very helpful comments.
Inference for Parameters Defined by Moment Inequalities: A Recommended Moment Selection Procedure
Article first published online: 26 NOV 2012
© 2012 The Econometric Society
Volume 80, Issue 6, pages 2805–2826, November 2012
How to Cite
Andrews, D. W. K. and Barwick, P. J. (2012), Inference for Parameters Defined by Moment Inequalities: A Recommended Moment Selection Procedure. Econometrica, 80: 2805–2826. doi: 10.3982/ECTA8166
- Issue published online: 26 NOV 2012
- Article first published online: 26 NOV 2012
- Manuscript received October, 2008; final revision received March, 2012.
- Asymptotic size;
- asymptotic power;
- confidence set;
- generalized moment selection;
- moment inequalities;
- partial identification;
- refined moment selection;
- unidentified parameter
This paper is concerned with tests and confidence intervals for parameters that are not necessarily point identified and are defined by moment inequalities. In the literature, different test statistics, critical-value methods, and implementation methods (i.e., the asymptotic distribution versus the bootstrap) have been proposed. In this paper, we compare these methods. We provide a recommended test statistic, moment selection critical value, and implementation method. We provide data-dependent procedures for choosing the key moment selection tuning parameter κ and a size-correction factor η.