Hi all,
I am trying to estimate a instrumented multi-level model
which resembles something of the sort:
xi: xtivreg DV IV1 (IV2 = IV3 IV4 IV5) i.IV6 i.IV7 i.V8
i.V9, re first
However, I find that I have rather different results
depending on the order the i.variables in the command (both
in the 1st and 2nd stage results). Does anybody know what
could be causing this? Thanks in advance for your help!
Regards,
Philippe
__________________________________
Philippe Jacquart
Graduate Assistant/Doctoral Student
University of Lausanne
Department of Management, HEC
Internef building, office 501.1
CH-1015 Lausanne
Tel. +41 (0)21 692 34 50 (GMT+1)
Fax +41 (0)21 692 34 95
*
* 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/
