Dear all,
Do the Sargan and Hansen J tests only apply if one has more IVs than endogenous regressors? These are overidentification tests, right?
How can I check if the IV violates the exclusion restriction is violated if there is only one IV and one endogenous regressor? No way I can show this is the case, right?
If I have doubts about whether my IV meets the exclusion restriction AND I have concerns about endogeneity...shall I "believe" the OLS estimates or shall I "believe" the 2SLS ones...Or probably none?
thanks
Happy holidays to all.
Carola
*
* 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/
