st: xtabond2

["Fausto Araujo" <ytcfausto@hotmail.com>]

  I�ve used xtabond2 because I had a problem with sargan test.
  In my equations, I use a exogenous variable (obit_nasc) like a instrument 
for lag depedent variable. The right way to type the formula is:

xtabond2 pcdin L(1/3).pcdin  pcpib eleicp ano,  twostep robust 
gmm(l4.(pcdin) pcpib eleicp ano) iv(obit_nasc)

  When I use this way, hansen test is a problem. But if I use a parsimony 
structure, I approve hansen test, like:

xtabond2 pcdin L(1/3).pcdin  pcpib eleicp ano,  twostep robust 
gmm(l4.(pcdin) ) iv(obit_nasc)

  My question is: Can I use the second way? it�s right?
  Does somebody have a bibliography about xtabond2 implementation?

  Thanks
  Fausto

_________________________________________________________________
Inscreva-se no novo Windows Live Mail beta e seja um dos primeiros a testar 
as novidades-gr�tis. Saiba mais: 
http://www.ideas.live.com/programpage.aspx?versionId=5d21c51a-b161-4314-9b0e-4911fb2b2e6d

*
*   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/