On 2004-11-03, at 13.40, Elmar Saathoff (compuserve.de) wrote:
you might want to try the ado "rdrr" which you can not download from
SSC but at
http://www.cceb.upenn.edu/localio/EPI521/
It estimates risk-ratios, -differences etc. after regression and the
helpfile states that it also
works after gllamm.
Thanks for letting me know about -rdrr-. I have just tried it and it
doesn't work on my -gllamm- because it seem sto be unable to handle the
ologit link. I tried it with a simple logit and compared the results I
got with the reults from the -nlcom- approach (3) I posted earlier
http://www.stata.com/statalist/archive/2004-11/msg00082.html.
Unfortunately, they do not agree. Neither the point estimate nor the
CIs are the same. I might have done something wrong when i specified my
model ... Anyway, I cannot use it for my current project but I might
have a closer look at it later on.
Michael
*
* 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/