Statalist The Stata Listserver


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: gllamm - score option


From   "Stas Kolenikov" <[email protected]>
To   [email protected]
Subject   Re: st: gllamm - score option
Date   Tue, 10 Apr 2007 22:29:20 -0500

Can you just incorporate your first stage into your -gllamm- model?
The whole idea of -gllamm- is to be able to model anything withing a
single model. That would improve efficiency, too.

The reason why -oprobit- can give you scores and -gllamm- (or rather
-gllapred-) cannot are both technical (the former is probably coded as
-ml lf- routine, and the latter, as -ml d0-), and conceptual: you need
to integrate over the random effects for pretty much anything in
-gllamm-, and score would be no exception. I would suspect it is
probably possible to compute the scores, at least conceptually, but
unless that option is readily available in -gllapred-, you don't want
to mess up with that.

On 4/10/07, [email protected] <[email protected]> wrote:
Dear All,

I need to obtain the score after running and ordered probit using the command
gllamm. The reason why I need to use this score option is that I have to
correct my standard errors due to the fact I am using a two stage procedure;
and I following the procedure in the Stata Journal (2006)- by A. R. Hole
(Calculating Murphy–Topel variance estimates in Stata: A simplified procedure).

I know I can get the score using oprobit. I.e., typing 'help oprobit
postestimation', I get the following information for the score option:
____________________________________________________________________________
scores calculates equation-level score variables.  The number of score variables
created will equal the number of outcomes in the model.  If the number of
outcomes in the model were k, the first new variable will contain the
derivative of the log likelihood with respect to the regression
equation, the other new variables will contain the derivative of the log
likelihood with respect to the cutpoints.
__________________________________________________________________________

Since the score option in glamm estimation seem to be invalid, my question is:
How can I get the equivalent of score for glamm? Is it posible?

Thank you very much for your help.

Marcos



*
*   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/


--
Stas Kolenikov
http://stas.kolenikov.name

*
*   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/



© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index