Hi Cristopher,
You can use Eviews 6.0. Open/create a data file (i.e. workfile), and click on the "Estimate VAR" on the "Quick" menu. A control panel will show up. On the panel, you can define your constraints under the "VEC Restrictions" and "Cointegration" menu.
--Ali Ozdogan
----- Original Message ----
From: Christopher Kam <[log in to unmask]>
To: [log in to unmask]
Sent: Wednesday, August 6, 2008 8:19:21 PM
Subject: [POLMETH] Identification via var-cov restrictions
Hi Folks,
I am trying to estimate a system of equations, and I would like to be able
to identify the system by constraining elements of the variance-covariance
matrix rather than by excluding an exogenous instrument from each equation
(as per Erikson & Palfrey 2000). The Stata folks tell me that there is no
command or .ado file to do this in Stata. 1) Does anybody know otherwise?
2) Can anybody recommend software that can do this? 3). and if the answer to
Question 2 is R, what library etc. do I need?
Thanks,
Chris
Christopher Kam
Assistant Professor
Department of Political Science
C-459 Buchanan, 1866 Main Mall
University of British Columbia
Vancouver, BC
CANADA
V6T 1Z1
Tel: 604-822-6606
Fax: 604-822-5540
**********************************************************
Political Methodology E-Mail List
Editors: Melanie Goodrich, <[log in to unmask]>
Delia Bailey, <[log in to unmask]>
**********************************************************
Send messages to [log in to unmask]
To join the list, cancel your subscription, or modify
your subscription settings visit:
http://polmeth.wustl.edu/polmeth.php
**********************************************************
**********************************************************
Political Methodology E-Mail List
Editors: Melanie Goodrich, <[log in to unmask]>
Delia Bailey, <[log in to unmask]>
**********************************************************
Send messages to [log in to unmask]
To join the list, cancel your subscription, or modify
your subscription settings visit:
http://polmeth.wustl.edu/polmeth.php
**********************************************************
|