I am fairly new to -xtabond2- command and I have some questions regarding the way for coding.
Here is what I typed:
Code:
xtabond2 winv L.winv wndf wdiv size wcf wmtb y2-y32, iv(size wmtb wcf y2-y32, eq(level)) gmm(L.winv, lag(2 4) eq(diff) collapse) gmm(L.winv, lag(2 4) eq(lev) collapse) gmm(wndf wdiv, lag(2 5) eq(diff) collapse) gmm(wndf wdiv, lag(2 5) eq(level) collapse) small robust twostep
* I treat L.winv wndf and wdiv as endogenous
* size, wcf and wmtb are exogenous
Here is what Stata provides:
Code:
. xtabond2 winv L.winv wndf wdiv size wcf wmtb y2-y32, iv(size wmtb wcf y2-y32, eq(
> level)) gmm(L.winv, lag(2 4) eq(diff) collapse) gmm(L.winv, lag(2 4) eq(lev) coll
> apse) gmm(wndf wdiv, lag(2 5) eq(diff) collapse) gmm(wndf wdiv, lag(2 5) eq(level
> ) collapse) small robust twostep
Favoring space over speed. To switch, type or click on mata: mata set matafavor spe
> ed, perm.
y2 dropped due to collinearity
y32 dropped due to collinearity
Warning: Two-step estimated covariance matrix of moments is singular.
Using a generalized inverse to calculate optimal weighting matrix for two-step es
> timation.
Difference-in-Sargan statistics may be negative.
Dynamic panel-data estimation, two-step system GMM
------------------------------------------------------------------------------
Group variable: companyno Number of obs = 5708
Time variable : datayearfi~l Number of groups = 502
Number of instruments = 55 Obs per group: min = 1
F(35, 501) = 8.26 avg = 11.37
Prob > F = 0.000 max = 30
------------------------------------------------------------------------------
| Corrected
winv | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
winv |
L1. | .0777343 .0238117 3.26 0.001 .0309512 .1245174
|
wndf | .4706236 .2684656 1.75 0.080 -.0568335 .9980807
wdiv | -.4705155 .588355 -0.80 0.424 -1.626463 .6854316
size | .0157155 .0052187 3.01 0.003 .0054623 .0259687
wcf | .0939375 .0381943 2.46 0.014 .0188967 .1689783
wmtb | .040033 .0187122 2.14 0.033 .003269 .076797
y3 | .2321169 .1283572 1.81 0.071 -.0200678 .4843016
y4 | .0437833 .0727516 0.60 0.548 -.0991524 .1867191
y5 | .0310705 .0607181 0.51 0.609 -.0882229 .1503639
y6 | .0225263 .0550617 0.41 0.683 -.085654 .1307066
y7 | .0220792 .0305908 0.72 0.471 -.0380229 .0821812
y8 | .0462088 .0320417 1.44 0.150 -.0167438 .1091614
y9 | .0609806 .0341976 1.78 0.075 -.0062078 .128169
y10 | .062331 .0418511 1.49 0.137 -.0198942 .1445562
y11 | .0833537 .0610176 1.37 0.173 -.0365282 .2032357
y12 | .0185959 .0423988 0.44 0.661 -.0647054 .1018972
y13 | -.0718608 .0371793 -1.93 0.054 -.1449075 .0011858
y14 | .0149272 .0346859 0.43 0.667 -.0532206 .0830751
y15 | .0713084 .039059 1.83 0.068 -.0054312 .148048
y16 | .1106499 .0416466 2.66 0.008 .0288264 .1924734
y17 | .0575054 .0461953 1.24 0.214 -.033255 .1482658
y18 | .1139996 .0518429 2.20 0.028 .0121433 .2158559
y19 | .1133759 .041656 2.72 0.007 .0315339 .1952179
y20 | .1672247 .0583108 2.87 0.004 .0526608 .2817885
y21 | .1393014 .0593121 2.35 0.019 .0227702 .2558325
y22 | .1218702 .0426705 2.86 0.004 .0380349 .2057054
y23 | .0449854 .0296588 1.52 0.130 -.0132854 .1032563
y24 | .1217456 .0513458 2.37 0.018 .0208661 .2226252
y25 | .0130082 .0281267 0.46 0.644 -.0422526 .068269
y26 | .0077887 .0227587 0.34 0.732 -.0369256 .052503
y27 | .0468559 .0370114 1.27 0.206 -.0258607 .1195725
y28 | -.0052972 .0308846 -0.17 0.864 -.0659764 .0553821
y29 | .0301708 .0283337 1.06 0.287 -.0254967 .0858383
y30 | -.0036861 .0323317 -0.11 0.909 -.0672085 .0598363
y31 | .0816127 .0326933 2.50 0.013 .0173798 .1458455
_cons | -.3291672 .1051305 -3.13 0.002 -.5357183 -.1226161
------------------------------------------------------------------------------
Instruments for first differences equation
GMM-type (missing=0, separate instruments for each period unless collapsed)
L(2/4).L.winv collapsed
L(2/5).(wndf wdiv) collapsed
Instruments for levels equation
Standard
_cons
size wmtb wcf y2 y3 y4 y5 y6 y7 y8 y9 y10 y11 y12 y13 y14 y15 y16 y17 y18
y19 y20 y21 y22 y23 y24 y25 y26 y27 y28 y29 y30 y31 y32
GMM-type (missing=0, separate instruments for each period unless collapsed)
DL(2/4).L.winv collapsed
DL(2/5).(wndf wdiv) collapsed
------------------------------------------------------------------------------
Arellano-Bond test for AR(1) in first differences: z = -6.76 Pr > z = 0.000
Arellano-Bond test for AR(2) in first differences: z = -0.13 Pr > z = 0.899
------------------------------------------------------------------------------
Sargan test of overid. restrictions: chi2(19) = 65.88 Prob > chi2 = 0.000
(Not robust, but not weakened by many instruments.)
Hansen test of overid. restrictions: chi2(19) = 19.92 Prob > chi2 = 0.400
(Robust, but can be weakened by many instruments.)
Difference-in-Hansen tests of exogeneity of instrument subsets:
GMM instruments for levels
Hansen test excluding group: chi2(8) = 8.32 Prob > chi2 = 0.403
Difference (null H = exogenous): chi2(11) = 11.60 Prob > chi2 = 0.395
gmm(L.winv, collapse eq(diff) lag(2 4))
Hansen test excluding group: chi2(16) = 17.31 Prob > chi2 = 0.366
Difference (null H = exogenous): chi2(3) = 2.60 Prob > chi2 = 0.457
gmm(L.winv, collapse eq(level) lag(2 4))
Hansen test excluding group: chi2(16) = 17.06 Prob > chi2 = 0.382
Difference (null H = exogenous): chi2(3) = 2.85 Prob > chi2 = 0.415
gmm(wndf wdiv, collapse eq(diff) lag(2 5))
Hansen test excluding group: chi2(11) = 11.86 Prob > chi2 = 0.374
Difference (null H = exogenous): chi2(8) = 8.05 Prob > chi2 = 0.428
gmm(wndf wdiv, collapse eq(level) lag(2 5))
Hansen test excluding group: chi2(11) = 11.85 Prob > chi2 = 0.375
Difference (null H = exogenous): chi2(8) = 8.06 Prob > chi2 = 0.427
.I appreciate any comment/help. Thanks!
0 Response to Coding for xtabond2
Post a Comment