On 2004-07-07, at 21.43, Clive Nicholas wrote:
Edlira Nazarani wrote:
I'm trying to run a mlogit using cross-sectional time series data.
Is it right to run as:
mlogit depvar indepvar , cluster i(ind)
or
should i use instead a xtlogit as:
xtlogit depvar indepvar,re i(ind)
If your dependent variable really is multinomial, my personal
preference
would be to use -mlogit- but, if possible, to use time dummies on the
RHS
of the equation. This should work especially if you have lots of
observations for each cross-section.
You could also estimate it as a random intercept model with -gllamm-.
. gllamm depvar indepvar , i(ind) link(mlogit) fam(binom) adapt trace
However, it may take some time to compute.
Michael
*
* 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/
