Free access to paper on dynamic panel data models
News
- Author: Statistics Views
- Date: 19 October 2015
Each week, we select a recently published article hot off the press and provide free access. This week's is from Journal of Applied Econometrics, and is currently available via Early View, where individual articles can be read prior to issue allocation.
To read the article in full, please click the link below:
Valentin Verdier
Journal of Applied Econometrics, Early View
DOI: 10.1002/jae.2486
This paper considers the estimation of dynamic panel data models when data are suspected to exhibit cross-sectional dependence. A new estimator is defined that uses cross-sectional dependence for efficiency while being robust to the misspecification of the form of the cross-sectional dependence. We show that using cross-sectional dependence for estimation is important to obtain an estimator that is more efficient than existing estimators. This new estimator also uses nuisance parameters parsimoniously so that it exhibits good small- and large-sample properties even when the number of time periods is large. As an empirical application, we estimate the effect of attending private school on student achievement using a value-added model.
Connect: