st: comparing predicted means within levels of a two category variable

[Andriene Simone Grant <granta@email.arizona.edu>]

Hello Statalisters,

I am interested in determining predicted mean values of a y variable
after adjustment for a two-category variable, race, and another
predictor, similar to ancova. I have therefore run a regression model
and the margins command, as follows:

regress y i.race predictor2
margins race

I am writing to confirm what the next step would be to determine
whether the predicted means for race=0 & race=1 are significantly
different from each other. Is this what contrast r.race would be
doing?

Thanks. I hope I can get a quick confirmation.

Andriene
PhD student
*
*   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/