I have a question regarding system-GMM. In this case, it seems that I have a two-step system GMM but I have not specified the instrument variables in the level equation. Is it correct to say that I am estimating a system-GMM, and not mention anything about the level equation?
Code:
. xtabond2 Y l.Y a b c ab ac coalition
> l.lngdp l.lngdppercapita l.gdpgrowth l.lninflation l.govtexp l.pop14 l.pop65, ///
> gmm(l.Y , lag(1 2) collapse eq(diff)) ///
> iv(a b c ab ac coalition l.lngdp l.lngdpperca
> pita l.gdpgrowth l.lninflation l.govtexp l.pop14 l.pop65, eq(diff)) ///
> nodiffsargan twostep robust
Favoring space over speed. To switch, type or click on mata: mata set matafavor speed
> , perm.
Dynamic panel-data estimation, two-step system GMM
------------------------------------------------------------------------------
Group variable: country Number of obs = 486
Time variable : year Number of groups = 26
Number of instruments = 16 Obs per group: min = 15
Wald chi2(14) = 146.89 avg = 18.69
Prob > chi2 = 0.000 max = 20
--------------------------------------------------------------------------------
| Corrected
Y | Coef. Std. Err. z P>|z| [95% Conf. Interval]
---------------+----------------------------------------------------------------
Y |
L1. | .7222813 .1701339 4.25 0.000 .388825 1.055738
|
a | -.2317608 .2530301 -0.92 0.360 -.7276908 .2641691
b | -.5301456 .5432221 -0.98 0.329 -1.594841 .5345502
c | -.0224109 .484336 -0.05 0.963 -.9716921 .9268703
ab | -.1367733 .3817006 -0.36 0.720 -.8848927 .611346
ac | -.0723654 .3836385 -0.19 0.850 -.8242831 .6795523
coalition | .2727919 .3676454 0.74 0.458 -.4477798 .9933636
|
lngdp |
L1. | -11.97239 5.726428 -2.09 0.037 -23.19598 -.7487975
|
lngdppercapita |
L1. | 10.03662 5.629337 1.78 0.075 -.9966812 21.06991
|
gdpgrowth |
L1. | -3.21324 4.289274 -0.75 0.454 -11.62006 5.193584
|
lninflation |
L1. | -.0736836 .0800735 -0.92 0.357 -.2306248 .0832577
|
govtexp |
L1. | 4.048511 4.055335 1.00 0.318 -3.8998 11.99682
|
pop14 |
L1. | -.1944994 .1995454 -0.97 0.330 -.5856012 .1966024
|
pop65 |
L1. | -.2088385 .1905127 -1.10 0.273 -.5822365 .1645594
|
_cons | 41.23084 18.69118 2.21 0.027 4.596788 77.86488
--------------------------------------------------------------------------------
Instruments for first differences equation
Standard
D.(a b c ab ac coalition L.lngdp
L.lngdppercapita L.gdpgrowth L.lninflation L.govtexp L.pop14 L.pop65)
GMM-type (missing=0, separate instruments for each period unless collapsed)
L(1/2).L.Y collapsed
Instruments for levels equation
Standard
_cons
------------------------------------------------------------------------------
Arellano-Bond test for AR(1) in first differences: z = -2.18 Pr > z = 0.029
Arellano-Bond test for AR(2) in first differences: z = 0.61 Pr > z = 0.544
------------------------------------------------------------------------------
Sargan test of overid. restrictions: chi2(1) = 1.69 Prob > chi2 = 0.194
(Not robust, but not weakened by many instruments.)
Hansen test of overid. restrictions: chi2(1) = 0.89 Prob > chi2 = 0.344
(Robust, but weakened by many instruments.)
.
end of do-file
Comment