xtabond2, Is my model valid?

[Hilal Baglitas]

I am trying lots of models about system GMM with xtabond2 command. But I always think are there any mistakes or missing things. The last estimation is below;

. xtabond2 lcoi L.lcoi L(0/1).(lints lfec) lto lrec lurb, gmm(L.coi lfec lurb, lag(1 2) collapse) iv(lints lrec lurb lfec lto, eq(diff)) robust

Favoring space over speed. To switch, type or click on mata: mata set matafavor speed, perm.

Dynamic panel-data estimation, one-step system GMM
------------------------------------------------------------------------------
Group variable: order Number of obs = 678
Time variable : year Number of groups = 36
Number of instruments = 15 Obs per group: min = 18
Wald chi2(8) = 18634.29 avg = 18.83
Prob > chi2 = 0.000 max = 19
------------------------------------------------------------------------------
| Robust
lcoi | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
lcoi |
L1. | .989838 .0411826 24.04 0.000 .9091217 1.070554
|
lints |
--. | .7950965 .1263377 6.29 0.000 .5474791 1.042714
L1. | -.8190855 .1211081 -6.76 0.000 -1.056453 -.581718
|
lfec |
--. | .6162121 .1860249 3.31 0.001 .25161 .9808141
L1. | -.6603453 .1931826 -3.42 0.001 -1.038976 -.2817144
|
lto | .0042994 .0205327 0.21 0.834 -.035944 .0445427
lrec | -.0168388 .015186 -1.11 0.268 -.0466028 .0129252
lurb | -.0718692 .1102335 -0.65 0.514 -.287923 .1441845
_cons | .5384129 .3911893 1.38 0.169 -.228304 1.30513
------------------------------------------------------------------------------
Instruments for first differences equation
Standard
D.(lints lrec lurb lfec lto)
GMM-type (missing=0, separate instruments for each period unless collapsed)
L(1/2).(L.coi lfec lurb) collapsed
Instruments for levels equation
Standard
_cons
GMM-type (missing=0, separate instruments for each period unless collapsed)
D.(L.coi lfec lurb) collapsed
------------------------------------------------------------------------------
Arellano-Bond test for AR(1) in first differences: z = -3.22 Pr > z = 0.001
Arellano-Bond test for AR(2) in first differences: z = -0.22 Pr > z = 0.826
------------------------------------------------------------------------------
Sargan test of overid. restrictions: chi2(6) = 19.59 Prob > chi2 = 0.003
(Not robust, but not weakened by many instruments.)
Hansen test of overid. restrictions: chi2(6) = 8.98 Prob > chi2 = 0.174
(Robust, but weakened by many instruments.)

Difference-in-Hansen tests of exogeneity of instrument subsets:
GMM instruments for levels
Hansen test excluding group: chi2(3) = 6.46 Prob > chi2 = 0.091
Difference (null H = exogenous): chi2(3) = 2.52 Prob > chi2 = 0.471
iv(lints lrec lurb lfec lto, eq(diff))
Hansen test excluding group: chi2(1) = 1.82 Prob > chi2 = 0.177
Difference (null H = exogenous): chi2(5) = 7.16 Prob > chi2 = 0.209

[Phil Bromiley]

You didn't get a quick answer. You'll increase your chances of a useful answer by following the FAQ on asking questions - provide Stata code in code delimiters, readable Stata output, and sample data using dataex. A fixed spacing font often makes Stata output easier to read.

Roodman has a good how-to paper on using GMM which you might look at and the documentation for xtabond2 might also be helpful See https://ideas.repec.org/a/tsj/stataj...i1p86-136.html