Cointegration and Long-Horizon Forecasting /

Imposing cointegration on a forecasting system, if cointegration is present, is believed to improve long-horizon forecasts. Contrary to this belief, at long horizons nothing is lost by ignoring cointegration when the forecasts are evaluated using standard multivariate forecast accuracy measures. In...

Full description

Bibliographic Details
Main Author: Diebold, Francis
Other Authors: Christoffersen, Peter
Format: Journal
Language:English
Published: Washington, D.C. : International Monetary Fund, 1997.
Series:IMF Working Papers; Working Paper ; No. 1997/061
Subjects:
Online Access:Full text available on IMF
Description
Summary:Imposing cointegration on a forecasting system, if cointegration is present, is believed to improve long-horizon forecasts. Contrary to this belief, at long horizons nothing is lost by ignoring cointegration when the forecasts are evaluated using standard multivariate forecast accuracy measures. In fact, simple univariate Box-Jenkins forecasts are just as accurate. Our results highlight a potentially important deficiency of standard forecast accuracy measures-they fail to value the maintenance of cointegrating relationships among variables-and we suggest alternatives that explicitly do so.
Item Description:<strong>Off-Campus Access:</strong> No User ID or Password Required
<strong>On-Campus Access:</strong> No User ID or Password Required
Physical Description:1 online resource (30 pages)
Format:Mode of access: Internet
ISSN:1018-5941
Access:Electronic access restricted to authorized BRAC University faculty, staff and students