Hi,
Can somebody tell me the difference between:
xtivreg y x1 x2 (x3 = x4) if (year==1978| year==1981), fe(ppn)
versus
taking three year differences of the data first and then running:
ivreg y x1 x2 (x3 = x4) if year==1981
I thought that when you have only two time periods running fixed effects
is exactly same as running it in time differences.
I did all my analysis the first way and then it turned out I have to
cluster so I switched to ivreg and everything changed!!!
So I need help desperately... If there is another problem than writing the
code wrong, any intuition on what the first regression tells???
mine
*
* 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/
