Hello, all
It may not matter much which one I use as the results are pretty
close. I still wonder why they are not the same. I thought both take
care of the endogeneity problem with probit estimations. ivprob gives
one equation while cdsimeq gives two simultaneous equations. Please
correct me if I got it wrong.
The commands I used are
.ivprob Indicator, endo(x) iv(a b) exog(c)
.cdsimeq (x a b) (Indicator c).
The coefficients and the standard errors are very close. For example,
-2.53 from ivprob before x while -2.48 in results from cdsimeq. The
p-values for the two coefficients are 1.65 and 1.56 respectively.
Just wondering......
Thanks,
Faye
*
* 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/