Hi everyone
My data is collected such that first classrooms and then students are
sampled (cluster sampling).
I am regressing boymid on video (categrorical variable). I am estimating
coefficients taking into account clustering. The following two commands give
nearly identical results.
xi: xtgee boymid i.video, i(classnum)
xi: regress boymid i.video, cluster(classnum)
I expected the gllamm command to also give identical results. While
coefficients are nearly identical to the results of the above two command,
SEs are considerably larger. Does anyone know why? Which command is more
appropriate for my analysis?
xi: gllamm boymid i.video,i(classnum)
thanks in advance
m
*
* 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/
