Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/201400 
Year of Publication: 
2007
Series/Report no.: 
DIW Discussion Papers No. 664
Version Description: 
Corrected version, December 17, 2007
Publisher: 
Deutsches Institut für Wirtschaftsforschung (DIW), Berlin
Abstract: 
In this paper, we make multi-step forecasts of the annual growth rates of the real GDP for each of the 16 German Länder (states) simultaneously. Beside the usual panel data models, such as pooled and fixed-effects models, we apply panel models that explicitly account for spatial dependence between regional GDP. We find that both pooling and accounting for spatial effects helps substantially improve the forecast performance compared to the individual autoregressive models estimated for each of the L¨ander separately. More importantly, we have demonstrated that effect of accounting for spatial dependence is even more pronounced at longer forecasting horizons (the forecast accuracy gain as measured by the root mean squared forecast error is about 9% at 1-year horizon and exceeds 40% at 5-year horizon). Hence, we strongly recommend incorporating spatial dependence structure into regional forecasting models, especially, when long-term forecasts are made.
Subjects: 
German Länder
forecasting
dynamic panel model
spatial autocorrelation
JEL: 
C21
C53
C23
Document Type: 
Working Paper

Files in This Item:
File
Size
305.99 kB





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.