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 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.
Publication date: May 1997
ISBN: 9781451848137
$15.00
Add to Cart by clicking price of the language and format you'd like to purchase
Available Languages and Formats
paperback else
English
Prices in red indicate formats that are not yet available but are forthcoming.
Topics covered in this book

This title contains information about the following subjects. Click on a subject if you would like to see other titles with the same subjects.

cointegration , forecasting , time series , econometrics , error variance

Summary