Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: Measures for goodness of fit in GLLAMM


From   "Mohammad Vesal" <m.vesal@gmail.com>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: Measures for goodness of fit in GLLAMM
Date   Sun, 18 May 2008 09:50:30 +0330

Dear Everyone,

I am using GLLAMM to estimate a MIMIC model (Logit measurement model &
linear SEM). I wonder what measures of fit can I calculate after estimating
GLLAMM.
I have found an example on GLLAMM website (blood.do) that calculates
Deviance for that model but I can't do the same thing for my model.

I also see another exam in section 9.4 of "GENERALIZED LATENT
VARIABLE MODELING" by Skrondal & Rabe-Hesketh that calculates Pearson X2 and
Deviance for a model like my model. But I can't find the calculations in the
do files for that example (Mislevy.do). My own calculations didn't match the
value showed in the book.

It would be great kindness of anyone who could help me in:
1. What are the formula for calculating Deviance & Pearson x2 from deviance
and pearson residuals? Is there any divion by something like degree of
freedom?
2. Is there any ado files that calculates some measures of fit after GLLAMM?

With many thanks,
Mohammad Vesal

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   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   |   What's new   |   Site index