Hi, when I re-ran some old -ivreg2- models using a newly downloaded -ivreg2- procedure, I found the F-statistics reported in the first stage are different now.
Is it becuase if I specify "robust", this new version -ivreg2- produces robust F-stat (as noted in the new output), while the old -ivreg2- that I downloaded about three years ago did not (even though I also specified "robust" when I ran the old one)?
Thanks,
Anne
*
* 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/
