re: st: ivreg, ivreg2 and select variables that have to be dropped

[Christopher Baum <kit.baum@bc.edu>]

<>
I am running instrumental variables estimations -- on Stata 10.

Surprisingly, with the same specification, results when I launch an ivreg are different of those when I launch an ivreg2!! I think it is because variables dropped in order to deal with collinearity are not the same in both estimations. What do you think?

Then, if I remember well a command allows to drop the same variables for both estimations -- or to select the variables that have to be dropped. However, I cannot find it. Could you help me please?



help _rmcoll  (underscore-rmcoll)

Kit



Kit Baum   |   Boston College Economics & DIW Berlin   |   http://ideas.repec.org/e/pba1.html
                              An Introduction to Stata Programming  |   http://www.stata-press.com/books/isp.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/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/