Title
|
Room
|
* ! Dynamic Model Specification Analysis
|
H-Madison
|
Date / Time
|
Sponsor
|
Type
|
08/05/2001
2:00 PM
-
3:50 PM
|
Business & Economics Statistics Section*
|
Invited
|
Organizer:
|
Marc Henry, Columbia University
|
Chair:
|
Marc Henry, Columbia University
|
Discussant:
|
|
Floor Discussion
|
3:45 PM
|
Description
The papers presented in this session propose simple ways of controlling the adequacy of a time series model to a specific predetermined objective (such as the estimation of a particular feature of the conditional distribution or of the spectral density function) irrespective of the overall correctness of the model specification. This approach may be applied to forecasting assessment and decision making with evolutive models in a context of high scientific uncertainty and constant information arrival.
|