Hi All,
I'm using xtmixed to estimate a 2-level hierarchical model. Data are
generated such that there is randomness only in the intercept. But I
am using xtmixed to estimate the general model, which allows
randomness in the slope coefficient too. So the estimate of one of the
level 2 variance parameters should be very close to 0. The command I'm
using is:
xtmixed ygi w x x_w || idschool: x, cov(unstructured) mle
However, xtmixed does not converge in this situation. It works fine
for data with standard structure error but never for data with random
effect structure error (randomness only in the intercept).
My question is: does anyone know how to make xtmixed work in this
situation or is there any other way to estimate the model?
Best,
Yali Wang
Michigan State Universtiy
*
* 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/
