Resource Center

Advanced Search
Technical Papers
Working Papers
Research Memoranda
GTAP-L Mailing List
GTAP FAQs
CGE Books/Articles
Important References
Submit New Resource

GTAP Resources: Resource Display

GTAP Resource #3506

"Bayesian validation of GTAP parameters on a large scale dynamic dataset"
by Lugovoy, Oleg and Vladimir Potashnikov


Abstract
The paper discusses a Bayesian approach to validation and estimation of GTAP parameters using additional information on economic dynamic from various sources. The approach combines non-linear programming optimization routine with Bayesian statistical inference. The feature of the approach is in integrity of GTAP theoretical structure during the estimation/validation process. The parameters are being estimated within the model, without relaxing general equilibrium assumption. All the variables in the model remain in equilibrium. Another feature is flexibility of the data requirements. There are no specific data requirements for the estimation/validation routine. Any information regarding economic dynamics, levels of variables, values of parameters can be naturally introduced into the estimation routine. In the paper we are implement the methodology to estimate CES production function elasticity parameters for 27 US industries on EU-KLEMS productivity database.


Resource Details (Export Citation) GTAP Keywords
Category: 2011 Conference Paper
Status: Published
By/In: Presented at the 14th Annual Conference on Global Economic Analysis, Venice, Italy
Date: 2011
Version:
Created: Lugovoy, O. (4/5/2011)
Updated: Lugovoy, O. (6/17/2011)
Visits: 1,908
- Software and modeling tools
- Dynamic modeling
- Calibration and parameter estimation


Attachments
If you have trouble accessing any of the attachments below due to disability, please contact the authors listed above.


Public Access
  File format Presentation (GTAP conference 2011)  (263.2 KB)   Replicated: 0 time(s)


Restricted Access
No documents have been attached.


Special Instructions
No instructions have been specified.


Comments (0 posted)
You must log in before entering comments.

No comments have been posted.