Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
| From | "Nick Cox" <n.j.cox@durham.ac.uk> |
| To | <statalist@hsphsun2.harvard.edu> |
| Subject | RE: st: ml with a parameter between 0.07 and 1 |
| Date | Thu, 25 Mar 2010 15:34:30 -0000 |
Is this a Crozza-Bond model? What happens if the magic number is not 0.07? Nick n.j.cox@durham.ac.uk Beatrice Crozza Dear Maarten and Paul, thank you very much. 2010/3/24 E. Paul Wileyto <epw@mail.med.upenn.edu>: > gen double `am'=0.07+(1-0.07)/(1+exp(-`a')) > Beatrice Crozza wrote: >> I did a maximum likelihood and I constrained one parameter to be >> between zero and one, in this way: >> >> gen double `am'=1/(1+exp(-`a')) >> >> and then I generated the standard error using the delta method. >> >> Now I want to constrain the parameter to be between 0.07 and 1. * * 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/