Hello all,
I am trying to estimate a multilevel (hierarchical) linear model using
"xtmixed". My data have three dimensions: product (introduced into a given
country from another country), country, time. Neither dimension is nested in
another dimension, I think. For example:
xtmixed y x1 x2 x3 || _all: R.country || _all: R.product
The problem is that one of independent variables may be endogenous. My
understanding is that xtmixed is based on random effect model which assumes
that no regressors are endogenous. Is there any way to estimate non-nested
hierarchical model with endogenous variable? Any suggestion would be
helpful.
Thank you in advance.
Mike.
*
* 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/
