Dear Statalist,
1. Could you please help me in interpreting the below results.
Difference-in-Hansen tests of exogeneity of instrument subsets:
GMM instruments for levels
Hansen test excluding group: chi2(19) = 29.20 Prob > chi2 = 0.063
Difference (null H = exogenous): chi2(16) = 13.00 Prob > chi2 = 0.672
gmm(AvQ SO sqSO, lag(3 3))
Hansen test excluding group: chi2(2) = 12.41 Prob > chi2 = 0.002
Difference (null H = exogenous): chi2(33) = 29.79 Prob > chi2 = 0.628
iv(IRisk D2007 D2008 D2009 D2010 D2011 D2012 D2013 D2014 D2015)
Hansen test excluding group: chi2(26) = 37.63 Prob > chi2 = 0.066
Difference (null H = exogenous): chi2(9) = 4.57 Prob > chi2 = 0.870
What does it mean by "Hansen test excluding group" and "Difference (null = exogenous)"?
2. Sometimes I found that Stata report that test without the second group (gmm(....)), like the results below. Could you please help me to explain why?
. xtabond2 AvQ LAvQ LO sqLO CtrlDum LOChange NoLO ATA Lev FixAGr LenInt, gmm (AvQ LO sqLO, lag(3 3)) iv(LenInt IRisk1
> D2007-D2015) artests(3) small noconstant twostep robust
Favoring space over speed. To switch, type or click on mata: mata set matafavor speed, perm.
Warning: Two-step estimated covariance matrix of moments is singular.
Using a generalized inverse to calculate optimal weighting matrix for two-step estimation.
Difference-in-Sargan/Hansen statistics may be negative.
Dynamic panel-data estimation, two-step system GMM
------------------------------------------------------------------------------
Group variable: ID Number of obs = 309
Time variable : Year Number of groups = 69
Number of instruments = 45 Obs per group: min = 1
F(10, 69) = 183.91 avg = 4.48
Prob > F = 0.000 max = 8
------------------------------------------------------------------------------
| Corrected
AvQ | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
LAvQ | .5670873 .0758761 7.47 0.000 .4157186 .7184559
LO | 5.203749 1.021265 5.10 0.000 3.166381 7.241116
sqLO | -4.549483 .7706978 -5.90 0.000 -6.086983 -3.011983
CtrlDum | -.3421226 .2036376 -1.68 0.097 -.7483684 .0641233
LOChange | .110238 .1233316 0.89 0.375 -.1358018 .3562778
NoLO | -.1132349 .0648383 -1.75 0.085 -.2425838 .0161141
ATA | 2.67e-08 2.17e-08 1.23 0.221 -1.65e-08 7.00e-08
Lev | -.3656472 .3235544 -1.13 0.262 -1.011121 .2798262
FixAGr | 4.07e-08 7.05e-08 0.58 0.566 -1.00e-07 1.81e-07
LenInt | -3.112551 .7225774 -4.31 0.000 -4.554053 -1.671048
------------------------------------------------------------------------------
Instruments for first differences equation
Standard
D.(LenInt IRisk1 D2007 D2008 D2009 D2010 D2011 D2012 D2013 D2014 D2015)
GMM-type (missing=0, separate instruments for each period unless collapsed)
L3.(AvQ LO sqLO)
Instruments for levels equation
Standard
LenInt IRisk1 D2007 D2008 D2009 D2010 D2011 D2012 D2013 D2014 D2015
GMM-type (missing=0, separate instruments for each period unless collapsed)
DL2.(AvQ LO sqLO)
------------------------------------------------------------------------------
Arellano-Bond test for AR(1) in first differences: z = -1.49 Pr > z = 0.136
Arellano-Bond test for AR(2) in first differences: z = -2.37 Pr > z = 0.018
Arellano-Bond test for AR(3) in first differences: z = 0.69 Pr > z = 0.492
------------------------------------------------------------------------------
Sargan test of overid. restrictions: chi2(35) = 84.91 Prob > chi2 = 0.000
(Not robust, but not weakened by many instruments.)
Hansen test of overid. restrictions: chi2(35) = 40.58 Prob > chi2 = 0.238
(Robust, but weakened by many instruments.)
Difference-in-Hansen tests of exogeneity of instrument subsets:
GMM instruments for levels
Hansen test excluding group: chi2(17) = 24.41 Prob > chi2 = 0.109
Difference (null H = exogenous): chi2(18) = 16.17 Prob > chi2 = 0.581
iv(LenInt IRisk1 D2007 D2008 D2009 D2010 D2011 D2012 D2013 D2014 D2015)
Hansen test excluding group: chi2(26) = 27.72 Prob > chi2 = 0.372
Difference (null H = exogenous): chi2(9) = 12.85 Prob > chi2 = 0.169
Thank you all so much for your kind help.
1. Could you please help me in interpreting the below results.
Difference-in-Hansen tests of exogeneity of instrument subsets:
GMM instruments for levels
Hansen test excluding group: chi2(19) = 29.20 Prob > chi2 = 0.063
Difference (null H = exogenous): chi2(16) = 13.00 Prob > chi2 = 0.672
gmm(AvQ SO sqSO, lag(3 3))
Hansen test excluding group: chi2(2) = 12.41 Prob > chi2 = 0.002
Difference (null H = exogenous): chi2(33) = 29.79 Prob > chi2 = 0.628
iv(IRisk D2007 D2008 D2009 D2010 D2011 D2012 D2013 D2014 D2015)
Hansen test excluding group: chi2(26) = 37.63 Prob > chi2 = 0.066
Difference (null H = exogenous): chi2(9) = 4.57 Prob > chi2 = 0.870
What does it mean by "Hansen test excluding group" and "Difference (null = exogenous)"?
2. Sometimes I found that Stata report that test without the second group (gmm(....)), like the results below. Could you please help me to explain why?
. xtabond2 AvQ LAvQ LO sqLO CtrlDum LOChange NoLO ATA Lev FixAGr LenInt, gmm (AvQ LO sqLO, lag(3 3)) iv(LenInt IRisk1
> D2007-D2015) artests(3) small noconstant twostep robust
Favoring space over speed. To switch, type or click on mata: mata set matafavor speed, perm.
Warning: Two-step estimated covariance matrix of moments is singular.
Using a generalized inverse to calculate optimal weighting matrix for two-step estimation.
Difference-in-Sargan/Hansen statistics may be negative.
Dynamic panel-data estimation, two-step system GMM
------------------------------------------------------------------------------
Group variable: ID Number of obs = 309
Time variable : Year Number of groups = 69
Number of instruments = 45 Obs per group: min = 1
F(10, 69) = 183.91 avg = 4.48
Prob > F = 0.000 max = 8
------------------------------------------------------------------------------
| Corrected
AvQ | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
LAvQ | .5670873 .0758761 7.47 0.000 .4157186 .7184559
LO | 5.203749 1.021265 5.10 0.000 3.166381 7.241116
sqLO | -4.549483 .7706978 -5.90 0.000 -6.086983 -3.011983
CtrlDum | -.3421226 .2036376 -1.68 0.097 -.7483684 .0641233
LOChange | .110238 .1233316 0.89 0.375 -.1358018 .3562778
NoLO | -.1132349 .0648383 -1.75 0.085 -.2425838 .0161141
ATA | 2.67e-08 2.17e-08 1.23 0.221 -1.65e-08 7.00e-08
Lev | -.3656472 .3235544 -1.13 0.262 -1.011121 .2798262
FixAGr | 4.07e-08 7.05e-08 0.58 0.566 -1.00e-07 1.81e-07
LenInt | -3.112551 .7225774 -4.31 0.000 -4.554053 -1.671048
------------------------------------------------------------------------------
Instruments for first differences equation
Standard
D.(LenInt IRisk1 D2007 D2008 D2009 D2010 D2011 D2012 D2013 D2014 D2015)
GMM-type (missing=0, separate instruments for each period unless collapsed)
L3.(AvQ LO sqLO)
Instruments for levels equation
Standard
LenInt IRisk1 D2007 D2008 D2009 D2010 D2011 D2012 D2013 D2014 D2015
GMM-type (missing=0, separate instruments for each period unless collapsed)
DL2.(AvQ LO sqLO)
------------------------------------------------------------------------------
Arellano-Bond test for AR(1) in first differences: z = -1.49 Pr > z = 0.136
Arellano-Bond test for AR(2) in first differences: z = -2.37 Pr > z = 0.018
Arellano-Bond test for AR(3) in first differences: z = 0.69 Pr > z = 0.492
------------------------------------------------------------------------------
Sargan test of overid. restrictions: chi2(35) = 84.91 Prob > chi2 = 0.000
(Not robust, but not weakened by many instruments.)
Hansen test of overid. restrictions: chi2(35) = 40.58 Prob > chi2 = 0.238
(Robust, but weakened by many instruments.)
Difference-in-Hansen tests of exogeneity of instrument subsets:
GMM instruments for levels
Hansen test excluding group: chi2(17) = 24.41 Prob > chi2 = 0.109
Difference (null H = exogenous): chi2(18) = 16.17 Prob > chi2 = 0.581
iv(LenInt IRisk1 D2007 D2008 D2009 D2010 D2011 D2012 D2013 D2014 D2015)
Hansen test excluding group: chi2(26) = 27.72 Prob > chi2 = 0.372
Difference (null H = exogenous): chi2(9) = 12.85 Prob > chi2 = 0.169
Thank you all so much for your kind help.
