Eva wrote:
... However, this means that for each observation, cat1 is set to 1 for
some of the computations, leaving the values of cat2 and cat3
unchanged. But it is impossible for an observation to have cat1=1 and
cat2=1 at the same time. The interaction effects for these
observations seem rather hypothetical to me.
***
I agree with you. The problem occurs always with dummies for different
categories. I had the same problem but could use -margeff- which has an
option -dummies- that enables to take into account dummies from
categorical variables (you can do similar things with -mfx- and option
-at()-. Unfortunately that is not possible with -inteff- as far as I know.
Johannes
*
* 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/