Please, can someone help me with this issue:
1) What are the "serious" implications (if any) when the Sargan test
(from xtivreg) or the Hansen test (from ivreg2) for overidentifying
restrictions rejects the null that the overidentifying restrictions are
valid, apart from the fact that the structural estimates cannot be
uniquely identified from the reduced form estimates?
2) Would it be better to "force" identification (by reducing the number
of instruments) even though the instruments are jointly valid.
Thanks.
*
* 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/
