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 |
Fingerprint
Keywords
- Heteroskedasticity
- Instrumental variables
- Many instruments
- Overidentification tests
- Specifications tests
- Weak instruments
ASJC Scopus subject areas
- Economics and Econometrics
- Applied Mathematics
- History and Philosophy of Science
Cite this
Testing overidentifying restrictions with many instruments and heteroskedasticity. / Chao, John C.; Hausman, Jerry A.; Newey, Whitney K.; Swanson, Norman R.; Woutersen, Tiemen M.
In: Journal of Econometrics, Vol. 178, No. PART 1, 01.2014, p. 15-21.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Testing overidentifying restrictions with many instruments and heteroskedasticity
AU - Chao, John C.
AU - Hausman, Jerry A.
AU - Newey, Whitney K.
AU - Swanson, Norman R.
AU - Woutersen, Tiemen M
PY - 2014/1
Y1 - 2014/1
N2 - 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.
AB - 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.
KW - Heteroskedasticity
KW - Instrumental variables
KW - Many instruments
KW - Overidentification tests
KW - Specifications tests
KW - Weak instruments
UR - http://www.scopus.com/inward/record.url?scp=84889639229&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84889639229&partnerID=8YFLogxK
U2 - 10.1016/j.jeconom.2013.08.003
DO - 10.1016/j.jeconom.2013.08.003
M3 - Article
AN - SCOPUS:84889639229
VL - 178
SP - 15
EP - 21
JO - Journal of Econometrics
JF - Journal of Econometrics
SN - 0304-4076
IS - PART 1
ER -