Thank you very much to both Bobby Gutierrez and Joseph Coveney for your
helpful suggestions.
I have run Bobby Gutierrez's clogit_score on a small sample of my data and
it does exactly what I need.
Thank you again
Karyen
At 11:38 AM 7/28/2004 -0500, you wrote:
Karyen Chu <[email protected]> asked:
> I have run a McFadden's choice model using clogit and cannot find any
method
> for obtaining the score matrix since clogit is one of the commands without
> the score( ) option.
> I have consulted section 23.15 "Obtaining Scores" in the user manual and
> looked at and tried the commands estimates and ereturn. So far,
nothing has
> worked.
> I need the scores to perform a score test because the McFadden's Choice
> model that I have estimated is actually the constrained form of a more
> complicated model and I am trying to test the constraints using a score
test
> since the unconstrained model will be a bear to estimate.
Joseph Coveney <[email protected]> replied:
> Jeroen Weesie wrote a conditional logistic regression command, -clogit2-,
> that provides scores in order to work with his -suest-, which requires
> scores from the estimation commands.
From looking at -clogit2-, it appears to work only with one-success-per-group
estimation, which may be fine since Karen is fitting a choice model.
To obtain scores in the more general case, take a look at my -clogit_score-
command.
. net from http://www.stata.com/users/rgutierrez
--Bobby
[email protected]
*
* 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/
Karyen Chu
Dept of Economics
U.C. Berkeley
*
* 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/
