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]

Re: st: sd(constant) with xtmixed


From   Maarten Buis <maartenlbuis@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: sd(constant) with xtmixed
Date   Fri, 8 Feb 2013 12:14:00 +0100

On Fri, Feb 8, 2013 at 11:55 AM, Carmen Blanco wrote:
> In my multilevel estimation Stata reports me sd(constant)  at the
> level 95% of significance. Could someone tell me, please, how to
> calculate sd(constant) at the level 99% of significance in xtmixed
> estimation.

In a multilevel random effects model you assume that the constant
differs across higher level units (persons if you have multiple
measurement on the same persons, classrooms if you have students
nested in classrooms, herds if you have cows nested in herds, etc.).
You do not measure the different constants but assume that they follow
a normal distribution, and you estimate the standard deviation of that
distribution. That is what sd(constant) is. So there is no level of
significance associated with that estimate, the point estimate is just
what it is and it won't change if you change the level of
significance.

There is a level of significance associated with the confidence
interval around sd(constant). You can change that by adding the
-level(99)- option to your estimation command.

Hope this helps,
Maarten

---------------------------------
Maarten L. Buis
WZB
Reichpietschufer 50
10785 Berlin
Germany

http://www.maartenbuis.nl
---------------------------------
*
*   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