Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


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

Re: st: comparing two mim gllamm logistic models


From   jl591164@albany.edu
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: comparing two mim gllamm logistic models
Date   Mon, 7 Jun 2010 13:03:22 -0400 (EDT)

Thanks, Maarten. I am running a model included the orthpoly generated
polynomials of time.
For the second point, it seems to me that using the one half of the p
value will take care of the boundary issue.

Singer and Willett ("Applied longitudinal data analysis")recommended to
compare the deviance statistics(-2ll) of nested modelds with the degree of
freedom being the additional constrainted imposed. If i apply this methods
to the nested models comparisons in my case, then the question is how to
obtain the -2ll of each model fitted with -mim:gllamm-.

Is the log likelihood of the models save in a macro called
e(MIM_1_crittype) : "log likelihood"? How stata may show its value in
output? Any advice will be appreciated.
Junqing


> --- On Fri, 4/6/10, jl591164@albany.edu wrote:
>> I use -mim, cat(fit):gllamm- to fit three-level logistic
>> regression models. Now i need to compare the model fit of two nested
>> models, e.g. randome intercept models with and without a quadratic term
>> of time.
>
> Create the time and time^2 using -orthpoly-, than include those variables
> in your model, the test for the "square" term gives you the test whether
> or not the quadratic term improves the model fit. For more, see
> -help orthog-.
>
>> Another example of two nested models is a randome intercept model and a
>> randome intercept and random slope model. Do i compare the -2logL, AIC
>> and BIC of the two models of concern? If so, how do i obtain these model
>> fit statistics after fitting mim:gllamm models?
>
> This is a very hard problem, even without -mim-, as this is a test of a
> hypothesis on the edge of the parameter space. See -help j_chibar-.
>
> 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/
>

*
*   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/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index