Fleur,
I don't understand your point. Isn't it 3SLS=IV+FGLS?.
Therefore your "score" is the residual...right? -predict-
ML equivalent should be FIML, which follows the same
structure than Weibull's problem in Gould's book (MLE)
Maybe, Maarten has more suggestions.
Rodrigo.
----- Original Message -----
From: "fleur wouterse" <[email protected]>
To: <[email protected]>
Sent: Thursday, September 28, 2006 10:39 AM
Subject: st: re: 3sls robust standard error
Dear Rodrigo,
Thank you for your reply. I have (I think) read
everything there is to read on the _robust command in
the STATA manual and have consulted the User's guide.
The problem is not programming the _robust command but
obtaining the score variable which is needed to obtain
robust estimates. This option is not available after
3sls regression and can apparently only be obtained
with ML programming. Writing a ML program, however, is
very complex for a 3SLS estimation.
And I was looking for some more information on this
procedure.
Fleur
__________________________________________________
Do You Yahoo!?
Tired of spam? Yahoo! Mail has the best spam protection around
http://mail.yahoo.com
*
* 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/
*
* 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/