Multi-Step Estimation for Forecasting
We delineate conditions which favour multi-step, or dynamic estimation for multi-step forecasting. An analytical example shows how dynamic estimation (DE) may accomodateincorrectly-specified models as the forecast lead alters, improving forecast performance for some mis-specifications. However, in correctly-specified models, reducing finite-sample biases does not justify DR. In a Monte Carlo forecasting study for integrated processes, estimating a unit root in the presence of a neglected negative moving-average error may favour DR, though other solutions exist to that scenario. A second Monte Carlo study obtains the estimator biases and explains these using asymptotic approximations.
Year of publication: |
1996
|
---|---|
Authors: | Clements, Michael P. ; Hendry, David F. |
Institutions: | Department of Economics, University of Warwick |
Saved in:
Saved in favorites
Similar items by person
-
Quantile Forecasts of Daily Exchange Rate Returns from Forecasts of Realized Volatility
Clements, Michael P., (2006)
-
Explanations of the inconsistencies in survey respondents'forecasts
Clements, Michael P., (2008)
-
US inflation expectations and heterogeneous loss functions, 1968–2010
Clements, Michael P., (2012)
- More ...