Greetings
Sorry to jump in the middle of a conversation, but Tim Wade mentioned
a wish about being able to create interaction terms and mentioned
"desmat" for doing this. I also wanted to make a pitch for "xi3" for
doing this and then "postgr3" for graphing the predicted values
afterwards.
A quick rundown about "xi3" can be found at
http://www.ats.ucla.edu/stat/stata/faq/xi3.htm with more at
http://www.ats.ucla.edu/stat/stata/webbooks/reg/chapter5/statareg5.htm .
Information on "postgr3" can be found at
http://www.ats.ucla.edu/stat/stata/ado/analysis/postgr3.htm and an
example showing graphing a continuous by continuous interaction can be
found at http://www.ats.ucla.edu/stat/stata/code/graph_concon_int.htm .
But, please read the help file for "postgr3" and note its limitations.
As always, all visitors are welcome to our Stata Resources page at
http://www.ats.ucla.edu/stat/stata/ and our Stata Portal at
http://statcomp.ats.ucla.edu/stata/default.htm .
Happy computing,
Michael Mitchell
Statistical Consulting Group
UCLA Academic Technology Services
http://www.ats.ucla.edu/stat/
*
* 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/
