Dear listmembers,
I have recently updated Stata 9 to Stata 10 and since then I'm getting
quite different results using GLLAMM.
Most of these differences are negligible. Unfortunately there is a huge
difference in the following model. The significance of my
macro-indicator change from 0.000 to 0.839.
Does anybody have experienced anything similar?
christian
***********************************
Stata 9:
syntax: gllamm y x1 x2 ..... , i(id houseid country) f(binom)
link(logit) eform
log likelihood = -10548.014
number of level 1 units = 35107
number of level 2 units = 19113
number of level 3 units = 14473
number of level 4 units = 11
------------------------------------------------------------------------------
transfer | exp(b) Std. Err. z P>|z| [95% Conf.
Interval]
-------------+----------------------------------------------------------------
cohab | .8947632 .009594 -10.37 0.000 .8761556
.913766
*****************
Stata 10:
syntax: gllamm y x1 x2 ... , i(id houseid country) f(binom)
link(logit) eform
number of level 1 units = 35107
number of level 2 units = 19113
number of level 3 units = 14473
number of level 4 units = 11
log likelihood = -10549.061
------------------------------------------------------------------------------
transfer | exp(b) Std. Err. z P>|z| [95% Conf.
Interval]
-------------+----------------------------------------------------------------
cohab | .9983468 .0081377 -0.20 0.839 .9825239
1.014424
*
* 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/
