Hi,
Just to follow up with the earlier mail;
The three models
Model 1:
reg3 (depvar1 varlist1) (depvar2 varlist2) ... (depvarN varlistN),
exog(iv1 iv2) endog(endogvar1 endogvar2) sure
Model 2:
reg3 (depvar1 varlist1) (depvar2 varlist2) ... (depvarN varlistN), sure
Model 3:
sureg (depvar1 varlist1) (depvar2 varlist2) ... (depvarN varlistN)
are giving me the exact same results.
Whereas
Model 4:
reg3 (depvar1 varlist1) (depvar2 varlist2) ... (depvarN varlistN),
exog(iv1 iv2) endog(endogvar1 endogvar2) 3sls
gives a result totally different. Model 1-3 gives results which are very
much similar to simple OLS.
I am now a bit confused whether "sure" option with -reg3- is actually
doing an IV when I estimate it with endog() and exog() options.
Kindly help me with this. Thanking you in advance.
Rijo John.
*
* 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/
