出版社：Suntory Toyota International Centres for Economics and Related Disciplines
摘要：Nonparametric regression is developed for data with both a temporal and a cross-sectional dimension. The model includes additive, unknown, individual-speci c components and allows also for cross-sectional and temporal dependence and conditional heteroscedasticity. A simple nonparametric estimate is shown to be dominated by a GLS-type one. Asymptotically optimal bandwidth choices are justi ed for both estimates. Feasible optimal bandwidths, and feasi- ble optimal regression estimates, are asymptotically justi ed, with nite sample performance examined in a Monte Carlo study.
