Re: st: comparing two mim gllamm logistic models

[Maarten buis <maartenbuis@yahoo.co.uk>]

--- On Mon, 7/6/10, jl591164@albany.edu wrote:
> By variance, do you mean variance at each level of the
> models? 

Yes

> One model may have a smaller level-1 variance than another
> model, but a larger level-2 varince. Then it may be hard to
> say which model performs better. 

Level 1 variance is not the same as level 2 variance, So you
must consider each variance separately. 

> Also, how i may test whether they are different from zero? 

The point I made in the last three posts is that that test 
hasn't been invented yet for the multiple imputation case, 
primarily because that is a very hard problem.

-- 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/