Can someone please tell me if xtnbreg is appropriate to use for hierarchical
linear modeling. I have seen xtnbreg used to model hierarchical data under
the assumption that it allows the level 1 beta coefficients to vary across
the level 2 units. However, the explanation of xtnbreg specifically says
"random effects" does not refer to the xb term. My assumption is that it
allows the dispersion parameter to vary across those units.
Two questions:
Is xtnbreg appropriate to use for hierarchical linear modeling?
Is the dispersion parameter mentioned dealing with errors of the regression
or the overdispersion that makes the use of negative binomial preferable to
poisson.
Carter
*
* 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/
