Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: fixing variance parameters in xtmixed to do meta-analysis
From
"JVerkuilen (Gmail)" <[email protected]>
To
[email protected]
Subject
Re: st: fixing variance parameters in xtmixed to do meta-analysis
Date
Thu, 13 Sep 2012 18:46:58 -0400
On Thu, Sep 13, 2012 at 6:23 PM, Vince Wiggins, StataCorp
<[email protected]> wrote:
>
> You currently can't and I don't know any tricks to fake it. It is
> definitely on our list to provide these types of constraints, but I
> suspect it will be a while.
Thanks for the definitive answer, Vince. I figured it would be on your
list if it wasn't possible as it's incredibly useful for many models.
I couldn't figure out a way but there are folks who are better at
driving xtmixed than me who can make things happen.
I got something "close enough" using the very nice metaan program to
satisfy my immdediate need and I do have access to PROC MIXED so I can
get the "right" answer. Frankly it doesn't look like enough as these
effects seem to have some outliers so I might need to go full Bayes.
*
* 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/