A bootstrap approach to moment selection
This paper proposes a bootstrap-based procedure for selecting the best moment conditions among a set of correctly specified moment conditions. The proposed method can be motivated by Edgeworth expansions and chooses moment conditions that minimize the approximate coverage error of confidence intervals and hypothesis tests for parameters. Because of the analytical intractability of Edgeworth expansions, we estimate the coverage error by the bootstrap. The proposed method can be applied to a wide class of estimators for possibly non-linear and possibly dynamic models. We investigate the small sample performance of the proposed method in Monte Carlo experiments. Copyright Royal Economic Society 2006 Published by Blackwell Publishing Ltd, 9600 Garsington Road, Oxford OX4 2DQ, UK and 350 Main Street, Malden, MA, 02148, USA.
If you experience problems downloading a file, check if you have the proper application to view it first. In case of further problems read the IDEAS help page. Note that these files are not on the IDEAS site. Please be patient as the files may be large.
As the access to this document is restricted, you may want to look for a different version under "Related research" (further below) or search for a different version of it.
Volume (Year): 9 (2006)
Issue (Month): 1 (03)
|Contact details of provider:|| Postal: 2 Dean Trench Street, Westminster, SW1P 3HE|
Phone: +44 20 3137 6301
Web page: http://www.res.org.uk/
More information through EDIRC
|Order Information:||Web: http://www.ectj.org|