Forecasting by factors, by variables, by both or neither?
We consider forecasting with factors, variables and both, modeling in-sample using Autometrics so all principal components and variables can be included jointly, while tackling multiple breaks by impulse-indicator saturation. A forecast-error taxonomy for factor models highlights the impacts of loca...
| Main Authors: | , , |
|---|---|
| Format: | Journal article |
| Published: |
Elsevier
2013
|