Forecasting regional labor market developments under spatial heterogeneity and spatial correlation

Because of heterogeneity across regions, economic policy measures are increasingly targeted at the regional level, and the need for forecasts at the regional level is rapidly increasing. The data available to compute regional forecasts is usually based on a pseudo- panel of a limited number of observations over time, and a large number of areas (regions) strongly interacting with each other. The application of traditional time-series techniques to distinct time series of regional data is likely to be a suboptimal forecasting strategy. In the field of regional forecasting of socioeconomic variables, both linear and nonlinear models have recently been applied and evaluated. However, often such analyses ignore the spatial interactions among regions. We evaluate the ability of different statistical techniques - namely spatial error and spatial cross-regressive models - to correct for misspecifications due to neglected spatial correlation in the data. Our empirical application concerns short-term forecasts of employment in 326 West German regions; we find that the superimposed spatial structure that is required for the estimation of spatial models improves the forecasting performance of non-spatial models.