Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: Standard deviations from OLS fixed effects regressions


From   Chris <chris.stata@gmail.com>
To   statalist <statalist@hsphsun2.harvard.edu>
Subject   st: Standard deviations from OLS fixed effects regressions
Date   Thu, 6 Jun 2013 11:42:12 +0200

Dear Statalist,

I want to calculate summary statistics for two groups after
controlling for heterogeneity via fixed effects. Groups are denoted by
dummy D=1 and D=0. To do this, I run

xtreg depvar D, fe

Now the mean (after controlling for fixed effects) is just _cons (for
D=0) and _cons+_b[D] (for D=1). Clearly, standard errors are reported,
but I have no idea how to get the SD for each of the two group means.
(Just multiplying the SE of the constant with the number of
observations from the D=0 group doesn't give the right answer; I
checked without FE, i.e., reg). Using predict, one can obtain the mean
by averaging predictions over all observations of the group, but I can
hardly use

predict se, stdp

and average standard errors of individual predictions. But how else am
I going to get those SDs? Any help is very much appreciated.

(I posted this question also here with a more detailled description,
but I believe they are mostly using R:
http://stats.stackexchange.com/questions/60991/retrieving-standard-deviations-from-ols-estimates)
*
*   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/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index