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: GLLAMM for an ecological dataset with issues
From
Joerg Luedicke <[email protected]>
To
[email protected]
Subject
Re: st: GLLAMM for an ecological dataset with issues
Date
Tue, 12 Feb 2013 09:14:55 -0500
On Mon, Feb 11, 2013 at 8:27 PM, Benita Kaytor <[email protected]> wrote:
<snip>
> In order to relax the requirements of simpler models and use the data in their rawest form, I am attempting to use a GLLAMM.
<snip>
Just a little remark: it seems that the model you are trying to fit
with GLLAMM could be fitted with -xtmixed- as well/instead. In GLM
terms, for both -xtmixed- and your current GLLAMM specification, you
would assume a model from the Gaussian family with identity link.
However, I had the impression that this is actually not what you want,
given your zero-bounded, positively skewed outcome. You could try
GLLAMM with a log link, but that won't make it faster. :) As some
general advice, perhaps you could start with a subset of your data and
a simplified model, then work your way up in terms of model complexity
and eventually you may be able to have it run on your full data for
some days. In all likelihood, GLLAMM won't trash your computer!
Joerg
*
* 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/