st: collinear included instruments

[Kit Baum <baum@bc.edu>]

sacrificial lamb

Dipa said

Using ivreg2, stata9 automatically drops the excluded instruments  
first whenever they are collinear with the included instruments. Can  
anyone tell me how to do the reverse, that is, I want to retain the  
excluded instruments and drop the included instruments? I realize  
that the nocollin option stops searching for collinearities, but i  
want to include only the excluded instruments in the first stage and  
drop some of the included instruments from the first stage. Is there  
a way of doing it?


The authors of -ivreg2- went to considerable effort to ensure that it  
_would_ do what you do not want it to do. We believed that the  
specification of the model -- which variables are in the regressor  
list -- should remain intact, changing the list of excluded  
instruments where needed to prevent altering the specification. If  
you don't want that behavior, then remove the offending included  
instruments from the regressor list.


Kit Baum, Boston College Economics and DIW Berlin
http://ideas.repec.org/e/pba1.html
An Introduction to Modern Econometrics Using Stata:
http://www.stata-press.com/books/imeus.html


*
*   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/