Aggregation of Space-Time Processes

UCSD Economics Discussion Paper No. 2001-07

30 Pages Posted: 15 Jul 2001

See all articles by Raffaella Giacomini

Raffaella Giacomini

University College London - Department of Economics; University of California, Los Angeles - Department of Economics

Clive W. J. Granger

University of California, San Diego (UCSD) - Department of Economics; Tinbergen Institute

Date Written: May 2001

Abstract

In this paper we compare the relative efficiency of different methods of forecasting the aggregate of spatially correlated variables. Small sample simulations confirm the asymptotic result that improved forecasting performance can be obtained by imposing a priori constraints on the amount of spatial correlation in the system. One way to do so is to aggregate forecasts from a Space-Time Autoregressive model (Cliff et al., 1975), which offers a solution to the 'curse of dimensionality' that arises when forecasting with VARs. We also show that ignoring spatial correlation, even when it is weak, leads to highly inaccurate forecasts. Finally, if the system satisfies a 'poolability' condition, there is a benefit in forecasting the aggregate variable directly.

Keywords: Spatial Correlation, Aggregation, Forecast Efficiency, Space-Time Models

JEL Classification: C33, C43, C53

Suggested Citation

Giacomini, Raffaella and Granger, Clive W. J., Aggregation of Space-Time Processes (May 2001). UCSD Economics Discussion Paper No. 2001-07, Available at SSRN: https://ssrn.com/abstract=276642 or http://dx.doi.org/10.2139/ssrn.276642

Raffaella Giacomini (Contact Author)

University College London - Department of Economics ( email )

Gower Street
London WC1E 6BT, WC1E 6BT
United Kingdom

University of California, Los Angeles - Department of Economics ( email )

405 Hilgard Avenue
Box 951361
Los Angeles, CA 90095-1361
United States

Clive W. J. Granger

University of California, San Diego (UCSD) - Department of Economics ( email )

9500 Gilman Drive
La Jolla, CA 92093-0508
United States
858-534-3383 (Phone)
858-534-7040 (Fax)

Tinbergen Institute ( email )

Burg. Oudlaan 50
Rotterdam, 3062 PA
Netherlands

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
181
Abstract Views
2,185
rank
228,352
PlumX Metrics