hi,
I think you have to specify the outcome in gllapred.
This means that for each of the alternative you have to give a command like
gllapred prob1, mu marginal outcome(1)
gllapred prob2, mu marginal outcome(2)
gllapred prob3, mu marginal outcome(3)
hope this helps
anna
----- Original Message -----
From: "Adrian Gonzalez-Gonzalez" <[email protected]>
To: <[email protected]>
Sent: Friday, May 07, 2004 12:26 AM
Subject: st: gllapred error after gllamm
> Dear Statalisters
>
> I am using gllamm to estimate a conditional logit model with two random
> parameters and three categories/alternatives with Stata 7.
>
> gllamm altexp s8_Years s9_Years c8 c9 if z==1, nocons expand (altij choice
> o) base(0) i(group) link(mlogit) fam(binomial) nrf(2) eqs(s8_Ye s9_Ye)
> nip(3) trace
>
> After convergence, I have no problem getting the results displayed in a
> regression table using gllamm allc.
>
> However, I am getting an error r(198) when I tried to used the gllapred
> command:
>
> gllapred prob, mu marginal
> (mu will be stored in prob)
> invalid syntax
> r(198);
>
>
> Thanks a lot in advance for any help
>
> Adrian Gonzalez
> Ph.D Candidate
> Agricultural, Environmental and Development Economics
> The Ohio State University
>
> *
> * 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/
