Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: CIs for predicted probabilities from dynamic multinomial logit with random effects (Stata 13)


From   Stephani Jens <[email protected]>
To   "'[email protected]'" <[email protected]>
Subject   st: CIs for predicted probabilities from dynamic multinomial logit with random effects (Stata 13)
Date   Thu, 22 Aug 2013 12:54:22 +0000

Dear all,

I have estimated a dynamic multinomial logit model with random effects using the gsem-command in Stata 13. After having calculated predicted probabilities which take into account the random part by using predict after gsem, I need to also calculate confidence intervals for these predicted probabilities. I learned that one can use margins with the option fixedonly to calculate confidence intervals which consider the fixed part only. 

However, I have the impression that it is not possible to calculate the CI that take into account the random part here. Does anyone have a suggestion how to do this, or did I miss something? When I was using the gllamm-command for this model, the calculation of these CI was possible by using the adofile called ci_marg_mu after gllapred. 

Any suggestion or help is greatly appreciated.

Jens

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index