Dave,
If you have a simulataneous equation system, you need to test identification with the order or rank condition. The order condition is necessary for identification, whereas the rank condition is necessary and sufficient for identification. According to Maddala, G.S., if you have g endogenous variables in the system and k = number of (endogenous and exogenous) variables missing from the equation, then for exact identification you need
k=g-1. If k < g-1, then your equation is not identified.
The rank condition procedure can be found in G.S. Maddala on pp.350-354. See references to order condition on p.347. That is, Maddala, G.S.(2001), Introduction to Econometrics, Third Ed., Wiley:NY, pp.347-354.
Regards,
Bob Yaffee
2100 Linwood Avenue
Apt 19-W
Fort Lee, NJ
07024-3171
Phone: 201-242-3824
Fax: 201-242-3825
[email protected]
----- Original Message -----
From: David Han <[email protected]>
Date: Sunday, October 31, 2004 7:57 pm
Subject: st: model identification problem
> Hi, all,
>
> I use -ml- to estimate my model and the error information is that my
> model is possibly not identified. How can I check the identifiability
> of my model? Thanks a lot!
>
> Dave
> *
> * For searches and help try:
> * http://www.stata.com/support/faqs/res/findit.html
> * http://www.stata.com/support/statalist/faq
> * http://www.ats.ucla.edu/stat/stata/
>
begin:vcard
n:Yaffee;Robert A
fn:Robert A Yaffee, Ph.D.
tel;cell:917-445-2468
tel;fax:201-242-3825
tel;work:201-242-3824
org:Research/Statistical Consulting;
adr:;;2100 Linwood Avenue, Apt 19-W;Fort Lee;N.J.;07024;USA
version:2.1
email;internet:[email protected]
end:vcard
