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]

Re: st: negative variance components and xtmixed


From   Scott Baldwin <baldwinlist@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: negative variance components and xtmixed
Date   Sat, 30 Jun 2012 13:14:17 -0600

Hi Jordan, I am not aware of any way to allow variances to be negative
in xtmixed (i.e., nothing similar to the nobound option in SAS).
However, if you are fitting a random intercept model, you can model
the correlation within cluster (which can be negative) as an
alternative to modeling the variance among the cluster means (which is
what you are doing in a random intercept model). This has been
discussed previously -- for example, see the following thread:
http://www.stata.com/statalist/archive/2010-09/msg00149.html

Hope that helps.

Best,
Scott


On Sat, Jun 30, 2012 at 10:59 AM, Jordan Silberman
<silberman.stata@gmail.com> wrote:
> Hello,
>
> Can anyone tell me if xtmixed allows variance components to be negative? Is
> there an option I must specify after xtmixed that will cause xtmixed to
> allow negative variance components?
>
> Thanks,
> Jordan
> *
> *   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/

*
*   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