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 on April 23, and its replacement, statalist.org is already up and running.


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

st: Random Slopes and their Standard Errors with xtmixed


From   Nasos Roussias <nasos.roussias@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   st: Random Slopes and their Standard Errors with xtmixed
Date   Wed, 28 Jul 2010 11:27:37 +0300

Dear List Members,

I have a question about calculating 2nd-level random slopes and their
significance levels for a multilevel model.
I am calculating a two-level random slopes model using xtmixed with Stata 11.1.
I allow one variable's effects to vary at the 2nd level (country-level).
For this variable, i want to get the random slopes and their
corresponding standard errors for each of the 2nd-level countries, so
i can calculate whether each of the country slopes is significant or
not.

I can get the coefficient for each country slope by using the /predict
,reffects/ command and adding each country's random effects to the
grand slope.
I can also estimate whether each of the BLUPs themselves are
significantly different from the grand slope using the BLUPs standard
errors from the /predict ,reses/ command.
However, i have not been able to figure how to combine the information
from the BLUPs standard errors and the grand slope standard errors to
get an estimate of each country's slope standard error.
Can anyone help? Is there some canned command that does this?
If not, can someone tell me how to calculate it manually?

Thank you for your help
Nasos Roussias
*
*   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/


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