st: Combining factor variable categories

[Richard Williams <richardwilliams.ndu@gmail.com>]

I have a friend who wants to combine categories in a factor variable, 
e.g. 1, 2, 3 = 0, 4, 5 = 1. The challenge is that he wants to do 
different combos within the same model, e.g. use the 5 category 
version for main effects and a 2 category version for interactions. 
He wants margins to work correctly so he doesn't want to first 
compute different variables and then use them in the model, because 
margins wouldn't know, for example, that the 5 category version was 
related to the 2 category version.
I think you could do this via constraints, e.g. something like

webuse nhanes2f, clear
constraint 1 1b.health = 2.health
constraint 2 1b.health = 3.health
constraint 3 4.health = 5.health
logit diabetes i.health, constraint (1/ 3)

Is there some simpler way?

-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
HOME:   (574)289-5227
EMAIL:  Richard.A.Williams.5@ND.Edu
WWW:    http://www.nd.edu/~rwilliam

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/