Hi,
I have two interaction terms in my linear regression model, which looks like this:
xi: reg y i.x1*i.x2 i.x1*i.x3
so, the first term in each interaction is x1. I would like to include the main effect of x1 in the interaction term.
Normally, with only one interaction, I do this with .xi3 like this
xi3: reg y [email protected]
If I use xi3 in the first model then it looks like this:
xi3: reg y [email protected] [email protected]
but now I still have to use .lincom to calculate every linear combination of x1 that is possible.
Is there an easier way to do this?
Thanks,
Raoul
*
* 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/
