I have a question concerning the output of xtmelogit, as I am
comparing Stata and SAS outputs.
I have estimated a logistic regression model with crossed random
effects. In SAS, I used the GLIMMIX macro, and compared it to the
output of xtmelogit. The xtmelogit syntax we used was
xtmelogit y Kontext Zahl Oder Und Kompl Formel Irrel Unbek ||
_all:R.item || id:, var
Here comes my question: the xtmelogit output (below) does not provide
any results pertaining to the residual variance, in contrast to SAS.
However, I would like to compute Intraclass Correlations and need the
residual variance for that. Is it possible to get this information
under xtmelogit?
------------------------------------------------------------------------------
Random-effects Parameters | Estimate Std. Err. [95% Conf. Interval]
-----------------------------+------------------------------------------------
_all: Identity |
var(R.item) | .2021935 .1036386 .0740399 .5521646
-----------------------------+------------------------------------------------
id: Identity |
var(_cons) | 1.379988 .253633 .9625649 1.97843
------------------------------------------------------------------------------
LR test vs. logistic regression: chi2(2) = 186.41 Prob > chi2 = 0.0000
*
* 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/