Title: Nonparametric panel data models with cross-sectional dependence
Authors: Alexandra Soberon - Universidad de Cantabria (Spain) [presenting]
Juan Manuel Rodriguez-Poo - Universidad de Cantabria (Spain)
Peter Robinson - London School of Economics (United Kingdom)
Abstract: The asymptotic distribution for the local linear estimator in nonparametric panel data regression models is established when cross-sectional dependence is allowed. In order to take into account the information of the error covariance for estimates, a two step local linear regression technique is proposed. Sufficient conditions for its asymptotic normality are given and its efficiency gains relative to the standard nonparametric techniques is established. Asymptotically optimal bandwidth choices are justified for both estimates. Feasible optimal bandwidths, and feasible optimal regression estimates, are also asymptotically justified. The proposed estimators are augmented by a Monte Carlo study and they are also illustrated in an empirical analysis about the relationship between public debt, monetary policy and economic growth for eurozone countries.