Statistique des variables
Variable Obs Mean Std. Dev. Min Max
lPIBH 296 6.60208 .4110896 5.880279 7.454141
lGINI 296 3.74443 .170414 3.448399 4.033533
lDCMPO 296 2.883669 1.20595 .0629079 4.496383
lPIBH
L1. 288 6.596327 .4097039 5.880279 7.454141
lGINI
L1. 288 3.744771 .1700928 3.448399 4.033533
lACINF 295 2.760404 .4542719 2.38968 4.227565
lCE 296 26.44243 1.839344 19.55109 30.11948
lIPC 295 4.241289 .7006909 .1731126 4.74824
lSUBT 296 3.74796 1.677004 -.5108256 7.791886
Régression multiple
Equation 1
Source SS df MS Number of obs = 296
F(3, 292) = 21.53
Model 77.7215003 3 25.9071668 Prob > F = 0.0000
Residual 351.301637 292 1.2030878 R-squared = 0.1812
Adj R-squared = 0.1727
Total 429.023138 295 1.45431572 Root MSE = 1.0969
lDCMPO Coef. Std. Err. t P>|t| [95% Conf. Interval]
lPIBH .813374 .1957449 4.16 0.000 .4281242 1.198624
lGINI 1.898085 .375292 5.06 0.000 1.159464 2.636705
lRDM -.3839785 .0647359 -5.93 0.000 -.5113866 -.2565705
_cons -1.150988 1.884378 -0.61 0.542 -4.859673 2.557697
Equation 2
Source SS df MS Number of obs = 287
F(6, 280) = 5033.98
Model 47.2646139 6 7.87743564 Prob > F = 0.0000
Residual .438158643 280 .001564852 R-squared = 0.9908
Adj R-squared = 0.9906
Total 47.7027725 286 .166792911 Root MSE = .03956
lPIBH Coef. Std. Err. t P>|t| [95% Conf. Interval]
lGINI .0185843 .0154886 1.20 0.231 -.0119045 .0490731
lPIBH
L1. .9763097 .0083116 117.46 0.000 .9599486 .9926708
lACINF -.0029593 .0065323 -0.45 0.651 -.0158179 .0098993
lCE -.0002922 .003224 -0.09 0.928 -.0066385 .0060541
lIPC -.00699 .00548 -1.28 0.203 -.0177772 .0037972
lSUBT .0090536 .0030846 2.94 0.004 .0029816 .0151256
_cons .1065991 .083717 1.27 0.204 -.0581955 .2713937
Equation 3
Source SS df MS Number of obs = 287
F(6, 280) = 487.78
Model 7.45155835 6 1.24192639 Prob > F = 0.0000
Residual .712902401 280 .00254608 R-squared = 0.9127
Adj R-squared = 0.9108
Total 8.16446075 286 .028547066 Root MSE = .05046
lGINI Coef. Std. Err. t P>|t| [95% Conf. Interval]
lPIBH -.0025505 .0107632 -0.24 0.813 -.0237376 .0186365
lGINI
L1. .932659 .0194726 47.90 0.000 .8943278 .9709902
lACINF .0165913 .0082488 2.01 0.045 .0003538 .0328289
lCE -.0002442 .0041185 -0.06 0.953 -.0083514 .007863
lIPC .0082289 .0070251 1.17 0.242 -.0055998 .0220576
lSUBT -.0039373 .0039405 -1.00 0.319 -.011694 .0038195
_cons .2074183 .1067204 1.94 0.053 -.0026579 .4174945
Test de normalité des variables
Skewness/Kurtosis tests for Normality
joint
Variable Obs Pr(Skewness) Pr(Kurtosis) adj chi2(2) Prob>chi2
lDCMPO 296 0.0003 0.0000 . 0.0000
lGINI 296 0.1494 0.0000 32.29 0.0000
lPIBH 296 0.0047 0.0000 . 0.0000
lRDM 296 0.0009 0.7710 10.08 0.0065
Equation 2
Skewness/Kurtosis tests for Normality
joint
Variable Obs Pr(Skewness) Pr(Kurtosis) adj chi2(2) Prob>chi2
lPIBH 296 0.0047 0.0000 . 0.0000
lGINI 296 0.1494 0.0000 32.29 0.0000
lACINF 295 0.0000 0.0000 . 0.0000
lCE 296 0.0000 0.0000 42.60 0.0000
lIPC 295 0.0000 0.0000 . 0.0000
Equation 3
Skewness/Kurtosis tests for Normality
joint
Variable Obs Pr(Skewness) Pr(Kurtosis) adj chi2(2) Prob>chi2
lGINI 296 0.1494 0.0000 32.29 0.0000
lPIBH 296 0.0047 0.0000 . 0.0000
lACINF 295 0.0000 0.0000 . 0.0000
lCE 296 0.0000 0.0000 42.60 0.0000
lIPC 295 0.0000 0.0000 . 0.0000
lSUBT 296 0.1515 0.0165 7.40 0.0247
Estimation modèle à effet fixe eq1
Fixed-effects (within) regression Number of obs = 296
Group variable: CODE Number of groups = 8
R-sq: Obs per group:
within = 0.0739 min = 37
between = 0.0033 avg = 37.0
overall = 0.0009 max = 37
F(3,285) = 7.58
corr(u_i, Xb) = -0.1829 Prob > F = 0.0001
lDCMPO Coef. Std. Err. t P>|t| [95% Conf. Interval]
lPIBH -.4699006 .1341655 -3.50 0.001 -.7339817 -.2058195
lGINI .1220963 .1142709 1.07 0.286 -.1028258 .3470184
lRDM .0160311 .0252334 0.64 0.526 -.0336363 .0656986
_cons 5.176332 .9277541 5.58 0.000 3.350213 7.002451
sigma_u 1.2816241
sigma_e .24731352
rho .96409984 (fraction of variance due to u_i)
F test that all u_i=0: F(7, 285) = 779.80 Prob > F = 0.0000
Effet aléatoire eq1
Random-effects GLS regression Number of obs = 296
Group variable: CODE Number of groups = 8
R-sq: Obs per group:
within = 0.0739 min = 37
between = 0.0028 avg = 37.0
overall = 0.0007 max = 37
Wald chi2(3) = 22.59
corr(u_i, X) = 0 (assumed) Prob > chi2 = 0.0000
lDCMPO Coef. Std. Err. z P>|z| [95% Conf. Interval]
lPIBH -.4596062 .1334193 -3.44 0.001 -.7211032 -.1981091
lGINI .1273832 .1140072 1.12 0.264 -.0960668 .3508332
lRDM .0144943 .0251631 0.58 0.565 -.0348245 .063813
_cons 5.122361 1.041166 4.92 0.000 3.081713 7.16301
sigma_u 1.3623631
sigma_e .24731352
rho .96809719 (fraction of variance due to u_i)
Effet fixe eq2
Fixed-effects (within) regression Number of obs = 287
Group variable: CODE Number of groups = 8
R-sq: Obs per group:
within = 0.9314 min = 35
between = 0.9974 avg = 35.9
overall = 0.9889 max = 36
F(6,273) = 617.91
corr(u_i, Xb) = 0.7246 Prob > F = 0.0000
lPIBH Coef. Std. Err. t P>|t| [95% Conf. Interval]
lGINI -.0056138 .0202019 -0.28 0.781 -.0453852 .0341575
lPIBH
L1. .8773571 .0239657 36.61 0.000 .8301761 .9245382
lACINF .025434 .0227221 1.12 0.264 -.0192987 .0701667
lCE .0097936 .0051875 1.89 0.060 -.0004189 .0200061
lIPC -.0209889 .0067229 -3.12 0.002 -.0342243 -.0077535
lSUBT .0108927 .0033802 3.22 0.001 .0042381 .0175474
_cons .5572292 .1759647 3.17 0.002 .2108089 .9036495
sigma_u .03321017
sigma_e .03805145
rho .43237544 (fraction of variance due to u_i)
F test that all u_i=0: F(7, 273) = 4.23 Prob > F = 0.0002
Effet aléatoire eq2
Random-effects GLS regression Number of obs = 287
Group variable: CODE Number of groups = 8
R-sq: Obs per group:
within = 0.9305 min = 35
between = 0.9989 avg = 35.9
overall = 0.9904 max = 36
Wald chi2(6) = 7764.92
corr(u_i, X) = 0 (assumed) Prob > chi2 = 0.0000
lPIBH Coef. Std. Err. z P>|z| [95% Conf. Interval]
lGINI .0097256 .0186333 0.52 0.602 -.026795 .0462461
lPIBH
L1. .9361479 .0159379 58.74 0.000 .9049102 .9673855
lACINF .0142181 .0129098 1.10 0.271 -.0110846 .0395208
lCE .0040011 .0045035 0.89 0.374 -.0048255 .0128277
lIPC -.013295 .006189 -2.15 0.032 -.0254253 -.0011648
lSUBT .0098687 .0032715 3.02 0.003 .0034566 .0162807
_cons .2674035 .1248333 2.14 0.032 .0227347 .5120722
sigma_u .01527841
sigma_e .03805145
rho .13883536 (fraction of variance due to u_i)
Effet fixe eq3
Fixed-effects (within) regression Number of obs = 287
Group variable: CODE Number of groups = 8
R-sq: Obs per group:
within = 0.8676 min = 35
between = 0.9298 avg = 35.9
overall = 0.8879 max = 36
F(6,273) = 298.17
corr(u_i, Xb) = -0.2768 Prob > F = 0.0000
lGINI Coef. Std. Err. t P>|t| [95% Conf. Interval]
lPIBH -.0545386 .0323972 -1.68 0.093 -.1183188 .0092416
lGINI
L1. .879439 .0257104 34.21 0.000 .8288231 .9300549
lACINF .0852101 .0292493 2.91 0.004 .0276273 .1427929
lCE .0096004 .0067811 1.42 0.158 -.0037496 .0229503
lIPC -.0005501 .0089463 -0.06 0.951 -.0181625 .0170624
lSUBT -.0061167 .004464 -1.37 0.172 -.014905 .0026715
_cons .345708 .2326593 1.49 0.138 -.1123264 .8037424
sigma_u .03204092
sigma_e .04976988
rho .29301363 (fraction of variance due to u_i)
F test that all u_i=0: F(7, 273) = 2.11 Prob > F = 0.0423
Effet aléatoire eq3
Random-effects GLS regression Number of obs = 287
Group variable: CODE Number of groups = 8
R-sq: Obs per group:
within = 0.8632 min = 35
between = 0.9965 avg = 35.9
overall = 0.9127 max = 36
Wald chi2(6) = 2926.68
corr(u_i, X) = 0 (assumed) Prob > chi2 = 0.0000
lGINI Coef. Std. Err. z P>|z| [95% Conf. Interval]
lPIBH -.0025505 .0107632 -0.24 0.813 -.023646 .0185449
lGINI
L1. .932659 .0194726 47.90 0.000 .8944934 .9708245
lACINF .0165913 .0082488 2.01 0.044 .0004239 .0327587
lCE -.0002442 .0041185 -0.06 0.953 -.0083164 .007828
lIPC .0082289 .0070251 1.17 0.241 -.0055401 .0219979
lSUBT -.0039373 .0039405 -1.00 0.318 -.0116605 .0037859
_cons .2074183 .1067204 1.94 0.052 -.0017499 .4165865
sigma_u 0
sigma_e .04976988
rho 0 (fraction of variance due to u_i)
Hausman eq1
Coefficients
(b) (B) (b-B) sqrt(diag(V_b-V_B))
eq1 . Difference S.E.
lPIBH -.4699006 -.4596062 -.0102944 .0141307
lGINI .1220963 .1273832 -.0052869 .0077595
lRDM .0160311 .0144943 .0015368 .0018823
b = consistent under Ho and Ha; obtained from xtreg
B = inconsistent under Ha, efficient under Ho; obtained from xtreg
Test: Ho: difference in coefficients not systematic
chi2(3) = (b-B)'[(V_b-V_B)^(-1)](b-B)
= 0.85
Prob>chi2 = 0.8377
Hausman eq2
Coefficients
(b) (B) (b-B) sqrt(diag(V_b-V_B))
eq1 . Difference S.E.
lGINI -.0056138 .0097256 -.0153394 .007805
lPIBH
L1. .8773571 .9361479 -.0587907 .017898
lACINF .025434 .0142181 .0112159 .0186984
lCE .0097936 .0040011 .0057925 .0025746
lIPC -.0209889 -.013295 -.0076938 .0026256
lSUBT .0108927 .0098687 .0010241 .0008504
b = consistent under Ho and Ha; obtained from xtreg
B = inconsistent under Ha, efficient under Ho; obtained from xtreg
Test: Ho: difference in coefficients not systematic
chi2(6) = (b-B)'[(V_b-V_B)^(-1)](b-B)
= 13.10
Prob>chi2 = 0.0415
(V_b-V_B is not positive definite)
Hausman eq3
Coefficients
(b) (B) (b-B) sqrt(diag(V_b-V_B))
eq1 . Difference S.E.
lPIBH -.0545386 -.0025505 -.0519881 .0305571
lGINI
L1. .879439 .932659 -.05322 .0167882
lACINF .0852101 .0165913 .0686188 .028062
lCE .0096004 -.0002442 .0098446 .0053872
lIPC -.0005501 .0082289 -.008779 .0055393
lSUBT -.0061167 -.0039373 -.0021795 .0020976
b = consistent under Ho and Ha; obtained from xtreg
B = inconsistent under Ha, efficient under Ho; obtained from xtreg
Test: Ho: difference in coefficients not systematic
chi2(6) = (b-B)'[(V_b-V_B)^(-1)](b-B)
= 11.73
Prob>chi2 = 0.0683
(V_b-V_B is not positive definite)
Estimation GMM en système à deux niveau avec déviation
Equation 1
Favoring speed over space. To switch, type or click on mata: mata set matafavor
> space, perm.
Warning: Number of instruments may be large relative to number of observations.
Warning: Two-step estimated covariance matrix of moments is singular.
Using a generalized inverse to calculate optimal weighting matrix for two-ste
> p estimation.
Difference-in-Sargan/Hansen statistics may be negative.
Dynamic panel-data estimation, two-step system GMM
Group variable: CODE Number of obs = 288
Time variable : DATE Number of groups = 8
Number of instruments = 40 Obs per group: min = 36
Wald chi2(3) = 6.16 avg = 36.00
Prob > chi2 = 0.104 max = 36
Corrected
D.lDCMPO Coef. Std. Err. z P>|z| [95% Conf. Interval]
lPIBH .0735195 .0388305 1.89 0.058 -.002587 .1496259
lGINI .0400198 .0615123 0.65 0.515 -.0805421 .1605818
lRDM -.0315543 .0128597 -2.45 0.014 -.0567587 -.0063498
_cons .0586748 .3352736 0.18 0.861 -.5984493 .7157989
Instruments for orthogonal deviations equation
Standard
FOD.(lPIBH lGINI)
GMM-type (missing=0, separate instruments for each period unless collapsed)
L(1/36).lDCMPO collapsed
Instruments for levels equation
Standard
lPIBH lGINI
_cons
GMM-type (missing=0, separate instruments for each period unless collapsed)
D.lDCMPO collapsed
Arellano-Bond test for AR(1) in first differences: z = -1.39 Pr > z = 0.163
Arellano-Bond test for AR(2) in first differences: z = -0.43 Pr > z = 0.669
Sargan test of overid. restrictions: chi2(36) = 279.11 Prob > chi2 = 0.000
(Not robust, but not weakened by many instruments.)
Hansen test of overid. restrictions: chi2(36) = 4.28 Prob > chi2 = 1.000
(Robust, but weakened by many instruments.)
Difference-in-Hansen tests of exogeneity of instrument subsets:
GMM instruments for levels
Hansen test excluding group: chi2(35) = 4.29 Prob > chi2 = 1.000
Difference (null H = exogenous): chi2(1) = -0.00 Prob > chi2 = 1.000
iv(lPIBH lGINI)
Hansen test excluding group: chi2(34) = 3.60 Prob > chi2 = 1.000
Difference (null H = exogenous): chi2(2) = 0.68 Prob > chi2 = 0.713
Equation 2
Favoring speed over space. To switch, type or click on mata: mata set matafavor
> space, perm.
Warning: Number of instruments may be large relative to number of observations.
Warning: Two-step estimated covariance matrix of moments is singular.
Using a generalized inverse to calculate optimal weighting matrix for two-ste
> p estimation.
Difference-in-Sargan/Hansen statistics may be negative.
Dynamic panel-data estimation, two-step system GMM
Group variable: CODE Number of obs = 287
Time variable : DATE Number of groups = 8
Number of instruments = 228 Obs per group: min = 35
Wald chi2(6) = 999.73 avg = 35.88
Prob > chi2 = 0.000 max = 36
Corrected
D.lPIBH Coef. Std. Err. z P>|z| [95% Conf. Interval]
lGINI .4880758 .4714796 1.04 0.301 -.4360073 1.412159
lPIBH
L1. -.6353627 .2273643 -2.79 0.005 -1.080989 -.1897368
lACINF .3651086 .1588612 2.30 0.022 .0537463 .6764709
lCE .0505345 .0354601 1.43 0.154 -.018966 .120035
lIPC -.082293 .0412996 -1.99 0.046 -.1632388 -.0013472
lSUBT .0276136 .0293236 0.94 0.346 -.0298596 .0850869
_cons .2749522 2.180598 0.13 0.900 -3.998941 4.548845
Instruments for orthogonal deviations equation
Standard
FOD.(lGINI lACINF lCE lIPC lSUBT)
GMM-type (missing=0, separate instruments for each period unless collapsed)
L(1/36).(lPIBH lGINI lACINF lCE lIPC lSUBT) collapsed
Instruments for levels equation
Standard
lGINI lACINF lCE lIPC lSUBT
_cons
GMM-type (missing=0, separate instruments for each period unless collapsed)
D.(lPIBH lGINI lACINF lCE lIPC lSUBT) collapsed
Arellano-Bond test for AR(1) in first differences: z = -1.46 Pr > z = 0.145
Arellano-Bond test for AR(2) in first differences: z = 0.41 Pr > z = 0.680
Sargan test of overid. restrictions: chi2(221) = 288.67 Prob > chi2 = 0.001
(Not robust, but not weakened by many instruments.)
Hansen test of overid. restrictions: chi2(221) = 0.01 Prob > chi2 = 1.000
(Robust, but weakened by many instruments.)
Difference-in-Hansen tests of exogeneity of instrument subsets:
GMM instruments for levels
Hansen test excluding group: chi2(215) = 0.01 Prob > chi2 = 1.000
Difference (null H = exogenous): chi2(6) = -0.00 Prob > chi2 = 1.000
Equation 3
Favoring speed over space. To switch, type or click on mata: mata set matafavor
> space, perm.
Warning: Number of instruments may be large relative to number of observations.
Warning: Two-step estimated covariance matrix of moments is singular.
Using a generalized inverse to calculate optimal weighting matrix for two-ste
> p estimation.
Difference-in-Sargan/Hansen statistics may be negative.
Dynamic panel-data estimation, two-step system GMM
Group variable: CODE Number of obs = 287
Time variable : DATE Number of groups = 8
Number of instruments = 228 Obs per group: min = 35
Wald chi2(6) = 4.88 avg = 35.88
Prob > chi2 = 0.560 max = 36
Corrected
D.lGINI Coef. Std. Err. z P>|z| [95% Conf. Interval]
lPIBH -.7943164 .9203424 -0.86 0.388 -2.598154 1.009522
lGINI
L1. .2677442 .5402954 0.50 0.620 -.7912154 1.326704
lACINF .5204605 .6062555 0.86 0.391 -.6677786 1.7087
lCE .1069297 .0810622 1.32 0.187 -.0519493 .2658088
lIPC -.0288544 .1143409 -0.25 0.801 -.2529585 .1952498
lSUBT -.0276319 .0756945 -0.37 0.715 -.1759904 .1207266
_cons .2005088 2.560104 0.08 0.938 -4.817203 5.21822
Instruments for orthogonal deviations equation
Standard
FOD.(lPIBH lACINF lCE lIPC lSUBT)
GMM-type (missing=0, separate instruments for each period unless collapsed)
L(1/36).(lGINI lPIBH lACINF lCE lIPC lSUBT) collapsed
Instruments for levels equation
Standard
lPIBH lACINF lCE lIPC lSUBT
_cons
GMM-type (missing=0, separate instruments for each period unless collapsed)
D.(lGINI lPIBH lACINF lCE lIPC lSUBT) collapsed
Arellano-Bond test for AR(1) in first differences: z = -2.53 Pr > z = 0.011
Arellano-Bond test for AR(2) in first differences: z = 0.39 Pr > z = 0.698
Sargan test of overid. restrictions: chi2(221) = 282.65 Prob > chi2 = 0.003
(Not robust, but not weakened by many instruments.)
Hansen test of overid. restrictions: chi2(221) = 0.09 Prob > chi2 = 1.000
(Robust, but weakened by many instruments.)
Difference-in-Hansen tests of exogeneity of instrument subsets:
GMM instruments for levels
Hansen test excluding group: chi2(215) = 0.09 Prob > chi2 = 1.000
Difference (null H = exogenous): chi2(6) = -0.00 Prob > chi2 = 1.000
GMM en système à deux niveau sans déviation avec variation
Equation 1
Favoring speed over space. To switch, type or click on mata: mata set matafavor
> space, perm.
Dynamic panel-data estimation, two-step system GMM
Group variable: CODE Number of obs = 288
Time variable : DATE Number of groups = 8
Number of instruments = 6 Obs per group: min = 36
Wald chi2(3) = 2.98 avg = 36.00
Prob > chi2 = 0.394 max = 36
Corrected
D.lDCMPO Coef. Std. Err. z P>|z| [95% Conf. Interval]
lPIBH .1814882 .2180047 0.83 0.405 -.2457932 .6087695
lGINI .2509751 .3029941 0.83 0.407 -.3428826 .8448327
lRDM -.0683573 .1048927 -0.65 0.515 -.2739433 .1372286
_cons -.63907 2.205557 -0.29 0.772 -4.961883 3.683743
Instruments for first differences equation
Standard
D.(lPIBH lGINI)
GMM-type (missing=0, separate instruments for each period unless collapsed)
L(1/2).lDCMPO collapsed
Instruments for levels equation
Standard
lPIBH lGINI
_cons
GMM-type (missing=0, separate instruments for each period unless collapsed)
D.lDCMPO collapsed
Arellano-Bond test for AR(1) in first differences: z = -1.39 Pr > z = 0.164
Arellano-Bond test for AR(2) in first differences: z = -0.43 Pr > z = 0.667
Sargan test of overid. restrictions: chi2(2) = 204.90 Prob > chi2 = 0.000
(Not robust, but not weakened by many instruments.)
Hansen test of overid. restrictions: chi2(2) = 1.76 Prob > chi2 = 0.414
(Robust, but weakened by many instruments.)
Difference-in-Hansen tests of exogeneity of instrument subsets:
GMM instruments for levels
Hansen test excluding group: chi2(1) = 1.66 Prob > chi2 = 0.197
Difference (null H = exogenous): chi2(1) = 0.10 Prob > chi2 = 0.752
Equation 2
> twostep robust artests (2)
Favoring speed over space. To switch, type or click on mata: mata set matafavor
> space, perm.
Warning: Number of instruments may be large relative to number of observations.
Warning: Two-step estimated covariance matrix of moments is singular.
Using a generalized inverse to calculate optimal weighting matrix for two-ste
> p estimation.
Difference-in-Sargan/Hansen statistics may be negative.
Dynamic panel-data estimation, two-step system GMM
Group variable: CODE Number of obs = 287
Time variable : DATE Number of groups = 8
Number of instruments = 24 Obs per group: min = 35
Wald chi2(6) = 126.20 avg = 35.88
Prob > chi2 = 0.000 max = 36
Corrected
D.lPIBH Coef. Std. Err. z P>|z| [95% Conf. Interval]
lGINI -.5996833 .2593912 -2.31 0.021 -1.108081 -.0912859
lPIBH
L1. -.6008704 .6218842 -0.97 0.334 -1.819741 .6180002
lACINF .1682719 .3317912 0.51 0.612 -.4820269 .8185707
lCE -.0142619 .0539983 -0.26 0.792 -.1200965 .0915728
lIPC -.1183368 .0559227 -2.12 0.034 -.2279433 -.0087303
lSUBT .0989274 . . . . .
_cons 6.263832 1.75341 3.57 0.000 2.827212 9.700452
Instruments for first differences equation
Standard
D.(lGINI lACINF lCE lIPC lSUBT)
GMM-type (missing=0, separate instruments for each period unless collapsed)
L(1/2).(lPIBH lGINI lACINF lCE lIPC lSUBT) collapsed
Instruments for levels equation
Standard
lGINI lACINF lCE lIPC lSUBT
_cons
GMM-type (missing=0, separate instruments for each period unless collapsed)
D.(lPIBH lGINI lACINF lCE lIPC lSUBT) collapsed
Arellano-Bond test for AR(1) in first differences: z = -0.51 Pr > z = 0.612
Arellano-Bond test for AR(2) in first differences: z = -1.67 Pr > z = 0.096
Sargan test of overid. restrictions: chi2(17) = 270.89 Prob > chi2 = 0.000
(Not robust, but not weakened by many instruments.)
Hansen test of overid. restrictions: chi2(17) = 3.31 Prob > chi2 = 1.000
(Robust, but weakened by many instruments.)
Difference-in-Hansen tests of exogeneity of instrument subsets:
GMM instruments for levels
Hansen test excluding group: chi2(11) = 3.31 Prob > chi2 = 0.986
Difference (null H = exogenous): chi2(6) = 0.00 Prob > chi2 = 1.000
iv(lGINI lACINF lCE lIPC lSUBT)
Hansen test excluding group: chi2(12) = 0.54 Prob > chi2 = 1.000
Difference (null H = exogenous): chi2(5) = 2.77 Prob > chi2 = 0.735
Equation 3
> space, perm.
Warning: Number of instruments may be large relative to number of observations.
Warning: Two-step estimated covariance matrix of moments is singular.
Using a generalized inverse to calculate optimal weighting matrix for two-ste
> p estimation.
Difference-in-Sargan/Hansen statistics may be negative.
Dynamic panel-data estimation, two-step system GMM
Group variable: CODE Number of obs = 287
Time variable : DATE Number of groups = 8
Number of instruments = 24 Obs per group: min = 35
Wald chi2(6) = 95.91 avg = 35.88
Prob > chi2 = 0.000 max = 36
Corrected
D.lGINI Coef. Std. Err. z P>|z| [95% Conf. Interval]
lPIBH -.2114555 .0387836 -5.45 0.000 -.28747 -.1354409
lGINI
L1. -.8748091 . . . . .
lACINF .3208274 .2962317 1.08 0.279 -.259776 .9014308
lCE -.0172305 .0323311 -0.53 0.594 -.0805983 .0461373
lIPC -.0025359 .0418594 -0.06 0.952 -.0845788 .0795069
lSUBT .0136918 .0138932 0.99 0.324 -.0135384 .040922
_cons 4.205627 . . . . .
Instruments for first differences equation
Standard
D.(lPIBH lACINF lCE lIPC lSUBT)
GMM-type (missing=0, separate instruments for each period unless collapsed)
L(1/2).(lGINI lPIBH lACINF lCE lIPC lSUBT) collapsed
Instruments for levels equation
Standard
lPIBH lACINF lCE lIPC lSUBT
_cons
GMM-type (missing=0, separate instruments for each period unless collapsed)
D.(lGINI lPIBH lACINF lCE lIPC lSUBT) collapsed
Arellano-Bond test for AR(1) in first differences: z = . Pr > z = .
Arellano-Bond test for AR(2) in first differences: z = 1.44 Pr > z = 0.151
Sargan test of overid. restrictions: chi2(17) = 352.71 Prob > chi2 = 0.000
(Not robust, but not weakened by many instruments.)
Hansen test of overid. restrictions: chi2(17) = 0.63 Prob > chi2 = 1.000
(Robust, but weakened by many instruments.)
Difference-in-Hansen tests of exogeneity of instrument subsets:
GMM instruments for levels
Hansen test excluding group: chi2(11) = 1.45 Prob > chi2 = 1.000
Difference (null H = exogenous): chi2(6) = -0.82 Prob > chi2 = 1.000
iv(lPIBH lACINF lCE lIPC lSUBT)
Hansen test excluding group: chi2(12) = 2.05 Prob > chi2 = 0.999
Difference (null H = exogenous): chi2(5) = -1.42 Prob > chi2 = 1.000
.
GMM en système à deux niveaux sans variation sans déviation
Equation 1
Favoring speed over space. To switch, type or click on mata: mata set matafavor
> space, perm.
Dynamic panel-data estimation, two-step system GMM
Group variable: CODE Number of obs = 296
Time variable : DATE Number of groups = 8
Number of instruments = 6 Obs per group: min = 37
Wald chi2(3) = 62.09 avg = 37.00
Prob > chi2 = 0.000 max = 37
Corrected
lDCMPO Coef. Std. Err. z P>|z| [95% Conf. Interval]
lPIBH .1518951 1.118541 0.14 0.892 -2.040406 2.344196
lGINI .8432995 1.122784 0.75 0.453 -1.357317 3.043916
lRDM -.1116547 .1868122 -0.60 0.550 -.4777999 .2544905
_cons 1.260722 5.998572 0.21 0.834 -10.49626 13.01771
Instruments for first differences equation
Standard
D.(lPIBH lGINI)
GMM-type (missing=0, separate instruments for each period unless collapsed)
L(1/2).lDCMPO collapsed
Instruments for levels equation
Standard
lPIBH lGINI
_cons
GMM-type (missing=0, separate instruments for each period unless collapsed)
D.lDCMPO collapsed
Arellano-Bond test for AR(1) in first differences: z = -1.44 Pr > z = 0.149
Arellano-Bond test for AR(2) in first differences: z = -0.96 Pr > z = 0.336
Sargan test of overid. restrictions: chi2(2) = 104.76 Prob > chi2 = 0.000
(Not robust, but not weakened by many instruments.)
Hansen test of overid. restrictions: chi2(2) = 1.87 Prob > chi2 = 0.392
(Robust, but weakened by many instruments.)
Difference-in-Hansen tests of exogeneity of instrument subsets:
GMM instruments for levels
Hansen test excluding group: chi2(1) = 0.68 Prob > chi2 = 0.410
Difference (null H = exogenous): chi2(1) = 1.20 Prob > chi2 = 0.274
iv(lPIBH lGINI)
Hansen test excluding group: chi2(0) = 0.00 Prob > chi2 = .
Difference (null H = exogenous): chi2(2) = 1.87 Prob > chi2 = 0.392
Equation 2
Favoring speed over space. To switch, type or click on mata: mata set matafavor
> space, perm.
Warning: Number of instruments may be large relative to number of observations.
Warning: Two-step estimated covariance matrix of moments is singular.
Using a generalized inverse to calculate optimal weighting matrix for two-ste
> p estimation.
Difference-in-Sargan/Hansen statistics may be negative.
Dynamic panel-data estimation, two-step system GMM
Group variable: CODE Number of obs = 287
Time variable : DATE Number of groups = 8
Number of instruments = 24 Obs per group: min = 35
Wald chi2(6) = 126.23 avg = 35.88
Prob > chi2 = 0.000 max = 36
Corrected
lPIBH Coef. Std. Err. z P>|z| [95% Conf. Interval]
lGINI -.5996833 .2593903 -2.31 0.021 -1.108079 -.0912878
lPIBH
L1. .3991295 .621884 0.64 0.521 -.8197407 1.618
lACINF .1682719 .331791 0.51 0.612 -.4820265 .8185703
lCE -.0142619 .0539981 -0.26 0.792 -.1200963 .0915726
lIPC -.1183368 .0559227 -2.12 0.034 -.2279433 -.0087303
lSUBT .0989274 . . . . .
_cons 6.263832 1.753396 3.57 0.000 2.827239 9.700425
Instruments for first differences equation
Standard
D.(lGINI lACINF lCE lIPC lSUBT)
GMM-type (missing=0, separate instruments for each period unless collapsed)
L(1/2).(lPIBH lGINI lACINF lCE lIPC lSUBT) collapsed
Instruments for levels equation
Standard
lGINI lACINF lCE lIPC lSUBT
_cons
GMM-type (missing=0, separate instruments for each period unless collapsed)
D.(lPIBH lGINI lACINF lCE lIPC lSUBT) collapsed
Arellano-Bond test for AR(1) in first differences: z = -0.51 Pr > z = 0.612
Arellano-Bond test for AR(2) in first differences: z = -1.67 Pr > z = 0.096
Sargan test of overid. restrictions: chi2(17) = 270.89 Prob > chi2 = 0.000
(Not robust, but not weakened by many instruments.)
Hansen test of overid. restrictions: chi2(17) = 3.31 Prob > chi2 = 1.000
(Robust, but weakened by many instruments.)
Difference-in-Hansen tests of exogeneity of instrument subsets:
GMM instruments for levels
Hansen test excluding group: chi2(11) = 3.31 Prob > chi2 = 0.986
Difference (null H = exogenous): chi2(6) = -0.00 Prob > chi2 = 1.000
iv(lGINI lACINF lCE lIPC lSUBT)
Hansen test excluding group: chi2(12) = 0.54 Prob > chi2 = 1.000
Difference (null H = exogenous): chi2(5) = 2.77 Prob > chi2 = 0.735
Equation 3
Favoring speed over space. To switch, type or click on mata: mata set matafavor
> space, perm.
Warning: Number of instruments may be large relative to number of observations.
Warning: Two-step estimated covariance matrix of moments is singular.
Using a generalized inverse to calculate optimal weighting matrix for two-ste
> p estimation.
Difference-in-Sargan/Hansen statistics may be negative.
Dynamic panel-data estimation, two-step system GMM
Group variable: CODE Number of obs = 287
Time variable : DATE Number of groups = 8
Number of instruments = 24 Obs per group: min = 35
Wald chi2(6) = 95.91 avg = 35.88
Prob > chi2 = 0.000 max = 36
Corrected
lGINI Coef. Std. Err. z P>|z| [95% Conf. Interval]
lPIBH -.2114554 .0387838 -5.45 0.000 -.2874703 -.1354406
lGINI
L1. .1251909 . . . . .
lACINF .3208274 .2962318 1.08 0.279 -.2597762 .901431
lCE -.0172305 .0323311 -0.53 0.594 -.0805983 .0461373
lIPC -.0025359 .0418594 -0.06 0.952 -.0845788 .0795069
lSUBT .0136918 .0138932 0.99 0.324 -.0135384 .040922
_cons 4.205626 . . . . .
Instruments for first differences equation
Standard
D.(lPIBH lACINF lCE lIPC lSUBT)
GMM-type (missing=0, separate instruments for each period unless collapsed)
L(1/2).(lGINI lPIBH lACINF lCE lIPC lSUBT) collapsed
Instruments for levels equation
Standard
lPIBH lACINF lCE lIPC lSUBT
_cons
GMM-type (missing=0, separate instruments for each period unless collapsed)
D.(lGINI lPIBH lACINF lCE lIPC lSUBT) collapsed
Arellano-Bond test for AR(1) in first differences: z = . Pr > z = .
Arellano-Bond test for AR(2) in first differences: z = 1.44 Pr > z = 0.151
Sargan test of overid. restrictions: chi2(17) = 352.71 Prob > chi2 = 0.000
(Not robust, but not weakened by many instruments.)
Hansen test of overid. restrictions: chi2(17) = 0.63 Prob > chi2 = 1.000
(Robust, but weakened by many instruments.)
Difference-in-Hansen tests of exogeneity of instrument subsets:
GMM instruments for levels
Hansen test excluding group: chi2(11) = 1.45 Prob > chi2 = 1.000
Difference (null H = exogenous): chi2(6) = -0.82 Prob > chi2 = 1.000
iv(lPIBH lACINF lCE lIPC lSUBT)
Hansen test excluding group: chi2(12) = 2.05 Prob > chi2 = 0.999
Difference (null H = exogenous): chi2(5) = -1.42 Prob > chi2 = 1.000