re: Re: Re: RE: st: How to run 2SLS twice

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

<>
Just a follow-up. I was wondering how the problem below would change
if I had panel data. So, the first stage regression would be:
z2_it = d_i + b5 * x3_it + yr_t + v_it
z1_it = c_i + b3 * x2_it + b4 * z2_it + yr_t + u_it
y_it = a_i + b1 * x1_it + b2 * z1_it + yr_t + e_it
In this case, should I still just run ivreg2 twice as you suggested
before, with the addition of observation dummies and year dummies?

Just use xtreg, fe on each equation, including i.year as a regressor, and you should be able to get the estimates
of what you list here. It is not an IV problem.

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/