Hi,
I am trying to run xtabond2 (http://fmwww.bc.edu/RePEc/bocode/x/xtabond2.hlp) on an unbalanced panel that has 74 countries from 1980 to 2006.
Regardless of how I alter the lag structure of the my lagged DV, I obtain a non-significant hansen J statistic and a significant sargan statistic. The hansen test performs best if I limit the number of instruments that I am using. I know that these tests are crucial in the argument that the instruments being used are exogenous but do I need to find consistent results using both tests?
here is an example of the commands I am using:
xtabond2 sq_FemalesASR iGini ilog_healthpercap ilog_unieduexp ilog_fert ilog_eduexpGDPpercap year totalG, r two gmm(sq_FemalesASR, lag(1 2)) iv(iGini year ilog_healthpercap ilog_unieduexp ilog_fert ilog_eduexp GDPpercap year totalG)
** I have also tried this using 'collapse' after the gmm variable.
Thanks for the help in advance,
Allison
*
* 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/