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 on April 23, and its replacement, statalist.org is already up and running.


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

st: gllamm - variance and sample size


From   Dimitrije Tišma <dimitrijetisma@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   st: gllamm - variance and sample size
Date   Thu, 22 Apr 2010 12:52:20 +0200

Hi,

I am estimating in GLLAMM two multilevel random intercept models for
two populations of different sizes (ratio 5:1, roughly), but fairly
similar structure (in other words, I do not expect to find huge
difference between them). Dependent variable is state transition,
while one of the independent variables is current state duration. Now,
I have a strong impression that, in gllamm, state duration turns out
to have higher coefficients and be more statistically significant in
larger samples. In the smaller sample the variance of the random
effect is larger and the effect of state duration much weaker. Again,
the two populations are not expected to differ to the extent as to
have so different coefficients for state duration. Is my impression
correct and can this be corrected for with some gllamm syntax? Many
thanks in advance! Regards,

Dimitrije
*
*   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