BOOTSTRAP-BASED CRITICAL-VALUES FOR THE INFORMATION MATRIX TEST

Authors
Citation
Jl. Horowitz, BOOTSTRAP-BASED CRITICAL-VALUES FOR THE INFORMATION MATRIX TEST, Journal of econometrics, 61(2), 1994, pp. 395-411
Citations number
12
Categorie Soggetti
Social Sciences, Mathematical Methods",Economics,"Mathematical, Methods, Social Sciences
Journal title
ISSN journal
03044076
Volume
61
Issue
2
Year of publication
1994
Pages
395 - 411
Database
ISI
SICI code
0304-4076(1994)61:2<395:BCFTIM>2.0.ZU;2-0
Abstract
In finite samples, the true size of White's information matrix test of ten differs greatly from its nominal size based on asymptotic critical values. This paper shows how the bootstrap can be used to obtain impr oved finite-sample critical values. The results of Monte Carlo experim ents show that for the cases investigated, the bootstrap largely elimi nates the problem of incorrect finite-sample size. Moreover, when size -corrected critical values are used, forms of the test that have small size distortions with asymptotic critical values can have much lower power than forms that have large size distortions with asymptotic crit ical values.