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.
Year of publication: |
1997-05-01
|
---|---|
Authors: | Diebold, Francis X. ; Christoffersen, Peter F. |
Institutions: | International Monetary Fund (IMF) |
Saved in:
freely available
Saved in favorites
Similar items by person
-
Cointegration and Long-Horizon Forecasting
Diebold, Francis X., (1997)
-
Is Poland Ready for Inflation Targeting?
Christoffersen, Peter F., (1999)
-
Interest Rate Arbitrage in Currency Baskets; Forecasting Weights and Measuring Risk
Christoffersen, Peter F., (1999)
- More ...