Richard and Joseph,
Many thanks for your suggestions which I just read upon returning from my short leave. I downloaded xi3, and indeed it seems to be able to do what xi can't, namely interact two continuous variables (which is what I'm interested in). The only downside -- unless I'm missing something about the proper use of xi3 -- is that it automatically includes the lower order terms. Richard, you're right, in many contexts that is good, but oftentimes I just want to do, say,
tobit y x1_x2 x3 x4 , ll
However, when I type the command
xi3: tobit y x1*x2 x3 x4 , ll
I get identical results as if I typed
tobit y x1 x2 x1_x2 x3 x4 , ll
where I created the interaction x1_x2 through the gen command. So if I don't want lower-order terms, does that mean that I have to resort to generating interactions manually after all?
Tewodaj
~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~
Tewodaj Mogues
Dept. of Agricultural and Applied Economics
University of Wisconsin - Madison
427 Lorch St. #317, Taylor Hall
Madison, WI 53706
*
* 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/
