Re: st: 3 or 4-level hierarchical models with noncontinuous dv

[Daniel Marcelino <dmsilv@gmail.com>]

In addition what Maarten said, I like to say that is reasonable to ask
if you really need 4 level equation. I mean, is there remain variance
after you model 1, 2, and 3 levels? Theoretically it could be
possible, however, I never found it.

Daniel

On Fri, Aug 19, 2011 at 3:21 AM, Maarten Buis <maartenlbuis@gmail.com> wrote:
> On Fri, Aug 19, 2011 at 3:52 AM, Jana von Stein wrote:
>> I am looking for a way to run a 3- or 4-level hierarchical model with a
>> noncontinuous dependent variable (specifically a 5-point ordinal scale). Is
>> there a way to use Stata's XTMIXED for this purpose, or any other Stata
>> command?
>
> That sounds like a job for -gllamm-. You can install it by typing in
> Stata -ssc install gllamm-.
>
> -gllamm- is like a Swiss army knive: you can do about anything with
> it, but there are two downsides. First, in order to allow you to do
> about anything with it the syntax needs to be rather complex.
> Fortunately, there is a complete manual and many examples available at
> <www.gllamm.org>. Still using -gllamm- is not going to be as easy as
> using an average Stata command. Second for it to be so general it
> cannot use specialized, and thus faster, algorithms, so it is slow.
>
> Hope this helps,
> Maarten
>
> --------------------------
> Maarten L. Buis
> Institut fuer Soziologie
> Universitaet Tuebingen
> Wilhelmstrasse 36
> 72074 Tuebingen
> Germany
>
>
> http://www.maartenbuis.nl
> --------------------------
> *
> *   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/
>



-- 
About me: http://danielmarcelino.zip.net/

*
*   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/