Spatial Panel Data Forecasting over Different Horizons, Cross-Sectional and Temporal Dimensions

Empirical assessments of the forecasting power of spatial panel data econometric models are still scarcely available. Moreover, several methodological contributions rely on simulated data to showcase the potential of proposed methods. While simulations are obviously useful to evaluate the properties and forecasting power of competing estimators, the empirical set-ups of simulation studies are often based on strong assumptions regarding the shape and regularity of the statistical distribution of the variables involved. It is then worthy having, next to a simulation study, an assessment of econometric models on observed data. In this paper, we evaluate competing spatial (dynamic) panel methods on real data, selecting a number of data sets characterized by a range of different cross-sectional and temporal dimensions. Additionally, the different levels of spatial autocorrelation of the data are explicitly considered. We carry out our empirical exercise on regional unemployment data for France, Germany, Italy, Spain and Switzerland. Additionally, we test different forecasting horizons, in order to investigate the speed of deterioration of forecasting quality, and we evaluate the importance of considering national boundaries in forecasting regional data. We compare two classes of methods: spatial VAR and dynamic panel augmented by eigenvector spatial filtering.