Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Neil Shephard <nshephard@gmail.com> |
To | statalist@hsphsun2.harvard.edu |
Subject | Re: st: crossed 4-level linear analysis |
Date | Tue, 12 Jul 2011 10:34:25 +0100 |
On Tue, Jul 12, 2011 at 10:24 AM, Hommes Juliette (EDUC) <juliette.hommes@maastrichtuniversity.nl> wrote: > L.S., > > With great enthusiasm I've worked with STATA but now I've come across a problem that I cannot resolve so far. Therefore I hope you can give me a hand. > > I've collected repeated measurements (2) in two modules. Participants enrolled in the first module and were divided in groups randomly (n=30). After finishing the first module, the participants are again randomly assigned to groups (n=32). As such I've got four levels in my data structure with "crossed"data among the students/group levels: 1) Repeated measures, 2) Modules, 3) Students, 4) Groups. > > I've been using the xtmixed command, but I found that it could only be used for three levelled datasets (and/or crossed data). Do you have an idea to analyse the four levels in one model and account for the crossed nature of the data in STATA? I'm not certain whether it can handle what you want, but you might want to see if -gllamm- is of use here (http://www.gllamm.org/). Within Stata you can get a description using -ssc desc gllamm- Neil -- “Truth in science can be defined as the working hypothesis best suited to open the way to the next better one.” - Konrad Lorenz Email - nshephard@gmail.com Website - http://kimura.no-ip.org/ Photos - http://www.flickr.com/photos/slackline/ * * 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/