This article analyzes artificial neural networks (ANNs) as a method to compute employment forecasts at a regional level. The empirical application is based on employment data collected for 327West German regionsover a periodof fourteenyears. First, the authors compare ANNs to models commonly used in panel data analysis. Second, they verify, in the case of panel data, whether the common practice of combining forecasts of the computed models is able to produce more reliable forecasts. The technique currently employed by the German authorities to compute such regional employment forecasts is comparable to a simple naïve no-change model. For this reason, ANNs are also compared to this undemanding technique.
Andergassen, R., P. Nijkamp, and A. Reggiani. 2003. Analysis of regional labour market dynamics: In search of indications for self-organised criticality. Journal of Geographical Systems5: 275-290.
2.
Baltagi, B. H.2001. Econometric analysis of panel data. London: Wiley.
3.
Bellmann, L., and U. Blien. 2001. Wage curve analyses of establishment data from western Germany. Industrial and Labor Relations Review54: 851-863.
4.
Blanchard, O. J., and L. F. Katz. 1992. Regional evolutions. Brookings Papers on Economic Activity1:1-75.
5.
Blien, U., and A. Tassinopoulos. 2001. Forecasting regional employment with the ENTROP method. Regional Studies35: 113-124.
6.
Cheng, B., and D. M. Titterington. 1994. Neuralnetworks:A review froma statistical perspective. Statistical Science9: 2-30.
7.
Church, K. B., and S. P. Curram. 1996. Forecasting consumers’ expenditure: A comparison between econometric and neural network models. International Journal of Forecasting12: 255-267.
8.
Decressin, J., and A. Fatás.1995. Regional labour market dynamics in Europe. European Economic Review39: 1627-1655.
9.
Diebold, F. X., and L. Kilian. 2000. Unit-root tests are useful for selecting forecasting models. Journal of Business and Economic Statistics18: 265-273.
10.
Diebold, F. X., and R. S. Mariano. 1995. Comparing predictive accuracy. Journal of Business and Economic Statistics13: 253-263.
11.
Donaldson, R. G., and M. Kamstra. 1996. Forecast combining with neural networks. Journal of Forecasting15: 49-61.
12.
Fauvel, Y., A. Paquet, and C. Zimmerman. 1999. Short-term forecasting of national and provincial employment in Canada. Working Paper R-99-6E. Applied Research Branch, Strategic Policy, Human Resources Development Canada, Hull, Quebec.
13.
Fischer, M. M.2001a. Central issues in neural spatial interaction modeling: The model selection and the parameter estimation problem. In New analytical advances in transportation and spatial dynamics, ed. M. Gastaldi and A. Reggiani, 3-19. Aldershot, UK: Ashgate.
14.
Fischer, M. M.2001b. Neural spatial interaction models. In Geocomputational modelling, ed. M. M. Fischer and Y. Leung, 195-219. Heidelberg, Germany: Springer.
15.
Franses, P. H., and K. van Griensven. 1998. Forecasting exchangerates using neural networks for technical trading rules. Studies in Nonlinear Dynamics & Econometrics2: 109-116.
16.
Granger, C. W. J., and P. Newbold. 1986. Forecasting economic time series. Orlando, FL: Academic Press.
17.
Haag, G.2001. A neural network approach for mobility panel analysis. In Geocomputational modelling, ed. M. M. Fischer and Y. Leung, 220-235. Heidelberg, Germany: Springer.
18.
Herbrich, R., M. Keilbach, T. Graepel, P. Bollmann-Sdorra, and K. Obermayer. 1999. Neural networks in economics: Background, applications and new developments. In Computational techniques for modelling learning in economics, ed. T. Brenner, 169-193. Dordrecht, the Netherlands: Kluwer Academic.
19.
Himanen, V., P. Nijkamp, and A. Reggiani. 1998. Neural networks in transport application. Aldershot, UK: Ashgate.
20.
Hsiao, C.2003. Analysis of panel data. Cambridge: Cambridge University Press.
21.
Kaashoek, J. F., and H. K. van Dijk. 1997. A simple strategy to pruneneural networks with an application to economic time series. Discussion Paper 97-123/4. Rotterdam, the Netherlands: Tinbergen Institute.
22.
Krugman, P.1991. Geography and trade. Cambridge, MA: MIT Press.
23.
Krugman, P.1998. Space, the final frontier. Journal of Economic Perspectives12: 161-174.
24.
Kuan, C.-M., and T. Liu. 1995. Forecasting exchange rates using feedforward and recurrent neural networks. Journal of Applied Econometrics10: 347-364.
25.
Kuan, C.-M., and H. White. 1994. ANNs: An econometric perspective. Econometric Reviews13:1-91.
26.
Morgan, P., B. Curry, and M. Beynon. 2000. Pruning neural networks by minimization of the estimated variance. European Journal of Economic and Social Systems14: 1-16.
27.
Nijkamp, P., A. Reggiani, and E. Sabella. 2001. Neural network and spatial interaction analysis of european commodity flows. In New analytical advances in transportation and spatial dynamics, ed. M. Gastaldi and A. Reggiani, 89-115. Aldershot, UK: Ashgate.
28.
Pindyck, R. S., and D. L. Rubinfeld. 1998. Econometric models and economic forecasts. Boston: McGraw-Hill.
29.
Pizarro, J., E. Guerrero, and P. L. Galindo. 2000. A statistical model selection strategy applied to neural networks, proceedings of the European Symposium on Artificial Neural Networks, Bruges, Belgium, 55-60.
30.
Reggiani, A., T. de Graaff, and P. Nijkamp. 2002. Resilience: An evolutionary approach to spatial economic systems. Networks and Spatial Economics2: 211-229.
31.
Reggiani, A., P. Nijkamp, and E. Sabella. 2000. A comparative analysis of the performance of evolutionary algorithms. In Spatial economic science: New frontiers in theory and methodology, ed. A. Reggiani, 332-354. Berlin: Springer-Verlag.
32.
Stock, J. H., and M. W. Watson. 1998. A comparison of linear and nonlinear univariate models for forecasting macroeconomic time series. NBER Working Paper 6607. Cambridge, MA: National Bureau of Economic Research.
33.
Swanson, N. R., and H. White. 1997a. Forecasting economic time series using flexible versus fixed specification and linear versus nonlinear econometric models. International Journal of Forecasting13: 439-461.
34.
Swanson, N. R., and H. White. 1997b. A model selection approach to real-time macroeconomic forecasting using linear models and artificial neural networks. Review of Economic and Statistics79: 540-550.
35.
Taylor, J. C.1997. The historical background, handbook of neural computation 1. Pp. A1.1-A1.1:1-A1.1-1-A1.1:7-7. http://library.thinkquest.org/18242/data/resources/nnhistory.pdf?tqskip1=1&tqtime=0429.
