--- On Mon, 19/10/09, Stefan Baron wrote:
> My only problem is that I do not want to compare the overall
> probability for entering the other group. What I need is the
> additional effect for a factor change in education, if
> teamsize is low/medium/high.
That is a difficult problem, as is discussed for the
binary logit/probit case in:
http://www.stata-journal.com/article.html?article=st0063
Fortunately this problem only arrises when you want to compute
probabilities and does not arrise when you interpret the results
in terms of relative risk ratios/odds ratios, so I would advise
you to do just that.
Hope this helps,
Maarten
This ignores an other problem that is among others discussed here:
http://www.nd.edu/~rwilliam/oglm/RW_Hetero_Choice.pdf
The somewhat excagerated version of my opinion on this is that
there can be no solution to this problem, and one should not waste
their time worying about unsolvable problems. (It is however still
good to know the limits of what one is doing)
--------------------------
Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen
Germany
http://www.maartenbuis.nl
--------------------------
Send instant messages to your online friends http://uk.messenger.yahoo.com
*
* 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/
