Asymptotic Properties of the Hahn-Hausman Test for Weak Instruments
نویسنده
چکیده
This note provides the weak-instrument asymptotic distributions of Hahn and Hausman’s (2002) tests for instrument validity. These distributions are used to compute asymptotic rejection rates when instruments are weak and, as a special case, irrelevant. These tests were proposed as pretests, and the asymptotic properties of post-test inferences, conditional on the tests failing to reject instrument validity, are also examined. Monte Carlo simulations show that the weak-instrument asymptotic distributions provide good approximations to the finite sample distributions for samples of size 100. * We thank Gary Chamberlain and Jin Hahn for helpful discussions, and Jose Tessada for research assistance. This research was supported by NSF grant SBR-0214131.
منابع مشابه
Hahn-Hausman Test as a Specification Test∗
This paper develops a modified version of the Sargan (1958, Econometrica 26(3): 393-415) test statistic of overidentifying restrictions, and shows that it is numerically equivalent to the test statistic of Hahn and Hausman (2002, Econometrica 70(1): 163-189) up to a sign. The modified Sargan test is constructed such that its asymptotic distribution under the null hypothesis of correct specifica...
متن کاملWeak Instruments: Diagnosis and Cures in Empirical Econometrics
What is the weak instruments (WI) problem and what causes it? Universal agreement does not exist on these questions. We define weak instruments by two features: (1) 2SLS is badly biased toward the OLS estimate and alternative “unbiased” estimators such as LIML may not solve the problem and (2) the standard (first order) asymptotic distribution does not give an accurate framework for inference. ...
متن کاملThe Hausman Test and Weak Instruments
We consider the following problem. There is a structural equation of interest that contains an explanatory variable that theory predicts is endogenous. There are one or more instrumental variables that credibly are exogenous with regard to this structural equation, but which have limited explanatory power for the endogenous variable. Further, there is one or more potentially strong instrument...
متن کاملAsymptotic Normality of Single-Equation Estimators for the Case with a Large Number of Weak Instruments∗
This paper analyzes conditions under which various single-equation estimators are asymptotically normal in a simultaneous equations framework with many weak instruments. In particular, our paper adds to the many instruments asymptotic normality literature, including papers by Morimune (1983), Bekker (1994), Angrist and Krueger (1995), Donald and Newey (2001), Hahn, Hausman, and Kuersteiner (200...
متن کاملKernel Weighted GMM Estimators for Linear Time Series Models
This paper analyzes the higher order asymptotic properties of Generalized Method of Moments (GMM) estimators for linear time series models using many lags as instruments. A data dependent moment selection method based on minimizing the approximate mean squared error is developed. In addition, a new version of the GMM estimator based on kernel weighted moment conditions is proposed. It is shown ...
متن کامل