Dears
I`ve run two regresions, one for diff-GMM:
xtabond2 depvart8 depvart0 exo1 exo2, twostep small iv(exo1 exo2) noleveleq
and the other for sys-GMM:
xtabond2 depvart8 depvart0 exo1 exo2, twostep small iv(exo1 exo2)
Stata give me this results
xtabond2 depvart8 depvart0 exo1 exo2, twostep small iv(exo1 exo2) noleveleq
Favoring space over speed. See help matafavor.
depvar0 dropped due to collinearity
Arellano-Bond dynamic panel-data estimation, two-step difference GMM results
---------------------------------------------------------------------------
Group variable: pais Number of obs= 91
Time variable : yr Number of groups= 17
Number of instruments = 2 Obs per group: min 4
F(2, 16) = 1.79 avg = 5.35
Prob > F = 0.198 max 6
------------------------------------------------------------------------
| Coef. Std. Err. t P>|t| [95% Conf.int]
-------------+----------------------------------------------------------
exo1 | -4.527917 4.395808 -1.03 0.318 -13.84661 4.790779
exo2 | .5849943 .3462016 1.69 0.110 -.1489204 1.318909
------------------------------------------------------------------------
Warning: Uncorrected two-step standard errors are unreliable.
Hansen test of overid. restrictions: chi2(0) = 0.00 Prob > chi2= .
Arellano-Bond test for AR(1) in first differences: z = 2.58 Pr >z = .010
Arellano-Bond test for AR(2) in first differences: z = -1.22 Pr >z =0.224
---------------------------------------------------------------------------
.. xtabond2 depvart8 depvart0 exo1 exo2, twostep small iv(exo1 exo2)
Favoring space over speed. See help matafavor.
Equation not identified. Regessors outnumber instruments.
I`ve two questions
Why there is no coeficient for depvart0 in the diffGMM?
what is the problem in the second estimation (sysGMM)?
Thanks a lot
IR
*
* 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/
