Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: Question regarding GLLAMM

From   Shubhabrata Mukherjee <>
To   stata forum <>
Subject   st: Question regarding GLLAMM
Date   Wed, 11 Aug 2010 14:55:26 -0700 (PDT)


I want to fit a hierarchical model and was wondering if GLLAMM can be used to 
fit the model. My data loos like this:

    I have item responses (polytomous) from almost 12000 'patients'). They  
answer 14 questions (I1-I14) where some of the questions
are regarding their doctors and some regarding the clinic as a whole. I have 
three variables (characteristics) for patients:
ethnicity (white, black and hispanic), education (dichotomized) and age 
(continous) which I want to embed in the model.

  The number of doctors are 400. The data I have is cross-sectional. One patient 
is designated to a single doctor only.

   In the next level, the doctors fall under 8 different clinics. Again a doctor 
cannot be in more than one clinic.

   So I have this hierarchy: item responses --> patients --> doctors --> 

   In my case I have 14 response variables instead of one and I have this  
hierarchy. Can GLLAMM fit the following model? or will it
be too complicated?



*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index