Estimation of dynamic panel data models with cross-sectional dependence: using cluster dependence fo efficiency

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.