Abstract
This paper gives a test of overidentifying restrictions that is robust to many instruments and heteroskedasticity. It is based on a jackknife version of the overidentifying test statistic. Correct asymptotic critical values are derived for this statistic when the number of instruments grows large, at a rate up to the sample size. It is also shown that the test is valid when the number of instruments is fixed and there is homoskedasticity. This test improves on recently proposed tests by allowing for heteroskedasticity and by avoiding assumptions on the instrument projection matrix. This paper finds in Monte Carlo studies that the test is more accurate and less sensitive to the number of instruments than the Hausman-Sargan or GMM tests of overidentifying restrictions.
Original language | English (US) |
---|---|
Pages (from-to) | 15-21 |
Number of pages | 7 |
Journal | Journal of Econometrics |
Volume | 178 |
Issue number | PART 1 |
DOIs | |
State | Published - Jan 2014 |
Externally published | Yes |
Keywords
- Heteroskedasticity
- Instrumental variables
- Many instruments
- Overidentification tests
- Specifications tests
- Weak instruments
ASJC Scopus subject areas
- Economics and Econometrics