Dear Statalist,
The `absorb(varname)' in the `areg' specifies the categorical variable
which is to be included in the regression as if it were specified by
dummy variables. [Same is done with the command xtreg, fe i(clust)].
Typically when we have large number of dummies and we don't want the
coefficients of the dummies to be printed out in the regression result
window this `absorb(varname)' is a good way out.
I want to know if ivreg or ivreg2 in Stata support such a thing. Coz I
want to estimate a model 'areg y x1 x2 x3, absorb(clust)' where
clust is an indicator variable for different clusters and x1 is an
endogenous variable. I want to estimate this same model with an
instrumental variable for x1.
I went through the ivreg command but could not find such an option.
Can someone please suggest a way out?
Thanking you in advance
Rijo John.
*
* 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/
