Dear list,
I am trying to get an idea of how inefficient are my estimates when I
perform the regression described ignoring the add-up constraint (due to
the non-linearities on the rhs). Is there a way to get efficient estimates?
Any help on the matter is appreciated.
I have a panel of 160 regions, and regress the share of foreign labour in
each of them over the corresponding share of natives, by skill level. In
particular, for each skill level i, I estimate:
Fijt = constant + Nijt + Dijt + Dijt*Nijt + control variables-jt + error
where Fijt = share of foreigners of skill group i in region j at time t
Nijt = corresponding share amongst natives
Dijt = dummy indicating whether region j is abundant in skill i relative to
all regions at time t.Dji = 0 otherwise
The sum across Fijt and Nijt is 1.
Max Tani
School of Economics and Management
UNSW @ ADFA
Campbell, ACT 2606
Australia
*
* 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/
