st: Standard errors for difference-in-differences

[Michael Thiombendia <michael.thiombendia@gmail.com>]

Dear Colleagues,
I'm a relative novice, and I'm interested in calculating the standard
error on a difference-in-differences calculation.  I have two
categories (Treatment and Control) and two means (Year 1 and Year 2)
for each.  I've calculated the standard errors on the differences for
Treatment and for Control using -ttest-, but I haven't been able to
figure out what approach and command I should use for calculating the
standard error on the difference-in-differences ((A-B) - (C-D)).  The
independent variable is categorical, and the dependent variable is a
normally distributed interval variable.

                                     Year 1                   Year 2
                    Diff
Treatment                       A                            B
                 (A-B)
Control                            C                            D
                   (C-D)

                                                                 Diff
in Diff:          (A-B) - (C-D)

Any advice would be greatly appreciated.

Thanks,
Michael
*
*   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/