st: How do I test whether the time path of income differs between two groups?

[andreas nordset <andreas.nordset@gmail.com>]

Dear Listers,

I have one more question.

So I am regressing income on a set of "relative year" dummies to
capture how it develops around an event. Furthermore, I would like to
estimate two separate time paths for two separate groups, so I run:
- reg inc (ry_m2 ry ry_m1 ry_0 ry_p1 ry_p2) (iry_m2 iry iry_m1 iry_0
iry_p1 iry_p2) -
where the second set of dummies is the first one interacted with the
dummy for membership of the second group.

Then I predict point estimates. Then, separately for each of the two
groups, I summarize the point estimates by relative year and plot
these means:
- predict pinc, xb-
- sum pinc if ry_m2==1-  (and similarly for each of the other relative years).
I believe that standard deviation of each summary devided by sqrt(N)
will also give me the correct standard error of each such estimate,
but please feel free to correct me if I'm wrong here.

Now this allows me finally to plot two time paths of income, each with
a 95% confidence interval around them. In some relative years the
confidence intervals overlap and in others they don't.

Now here's the question: How do I appropriately test whether the time
paths of the two groups are significantly different? I suppose that in
any specific relative year they are if the two confidence intervals do
not overlap, but how can I do a joint test for all relative years?

Thank you very much for your replies and best regards,
Andreas
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/