Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
| From | David Hoaglin <dchoaglin@gmail.com> |
| To | statalist@hsphsun2.harvard.edu |
| Subject | Re: st: a question about -gllamm- model |
| Date | Sun, 25 Mar 2012 21:49:50 -0400 |
Andrew, Have you looked at the documentation for -gllapred-? I have the impression that its options include what you are looking for. To what extent do your data support changing that dichotomous predictor from 0 to 1 while holding the other predictors constant? You should check that you are not extrapolating beyond your data. The "held constant" interpretation generally oversimplifies what is going on. David Hoaglin 2012/3/25 Huaandrew <andrew0845@hotmail.com>: > Hi Statalisters: > > Is there a way that I can estimate the changes in probability(the dependent variable) that result from changing a dichotomous independent variable from 0 to 1 (while holding all other independent variables constant) in a gllamm model? As far as I know, the gllamm model is not supported by Clarify. I believe that there is another way through Stata to complete this sort of simulation (under the estimated parameters of the model), but I do not know exactly how or what the exact command would be. Any insight you might have would be greatly appreciated! > > Andrew * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/