In this paper, we investigate a dynamic linear panel regression model with measurement error. We consider the panel data estimation whose time dimension (T) is not small and comparable to the cross sectional dimension (N). First, we show that the 2SLS estimator suffers from the bias problem due to many instrumental variables. Using the alternative asymptotics where [Formula presented] goes to a constant as N,T→∞, we characterize its asymptotic bias due to many IVs. As a bias reduction method, we investigate the JIVE and derive its limiting distribution under the alternative asymptotics.
Bibliographical noteFunding Information:
We thank Tom Wansbeek and two referees for helpful comments. We also appreciate the comments from Xu Cheng and the conference participants of the 2014 ASSA winter meeting in Philadelphia. Moon acknowledges that this work was supported by the National Research Foundation of Korea Grant funded by the Korean Government (NRF-2014S1A5A8012177).
All Science Journal Classification (ASJC) codes
- Economics and Econometrics