An Open-model Forecast-error Taxonomy
We develop forecast-error taxonomies when there are unmodeled variables, forecast 'off-line'.� We establish three surprising results.� Even when an open system is correctly specified in-sample with zero intercepts, despite known future values of strongly exogenous variables, changes in dynamics can induce forecast failure when they have non-zero means.� The additional impact on forecast failure of incorrectly omitting such variables depends only on shifts in their means.� With no such shifts, there is no reduction in forecast failure from forecasting unmodeled variables relative to omitting them in 1-step or multi-step forecasts.� Simulation illustrations confirm these results.
|Date of creation:||01 Jun 2011|
|Date of revision:|
|Contact details of provider:|| Postal: |
Web page: http://www.economics.ox.ac.uk/
More information through EDIRC
When requesting a correction, please mention this item's handle: RePEc:oxf:wpaper:552. See general information about how to correct material in RePEc.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (Caroline Wise)
If references are entirely missing, you can add them using this form.