一阶sys-GMM模型
. xtabond2 lntotdebt L.lntotdebt L(0/1).(lnprofit lnasset lnfinafee lnsale),gmmstyle(L.lntotd
> ebt)ivstyle(L2.lntotdebt L(0/2).(lnprofit lnasset lnfinafee lnsale))robust small
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 robust weighting matrix for Hansen test.
Difference-in-Sargan/Hansen statistics may be negative.
Dynamic panel-data estimation, one-step system GMM
------------------------------------------------------------------------------
Group variable: i Number of obs = 23792
Time variable : year Number of groups = 11304
Number of instruments = 40 Obs per group: min = 0
F(9, 11303) = 13634.05 avg = 2.10
Prob > F = 0.000 max = 6
------------------------------------------------------------------------------
| Robust
lntotdebt | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
lntotdebt |
L1. | .8127749 .0075761 107.28 0.000 .7979244 .8276253
lnprofit |
--. | -.0365713 .0049212 -7.43 0.000 -.0462177 -.0269249
L1. | -.0165535 .00466 -3.55 0.000 -.025688 -.007419
lnasset |
--. | .2516595 .0160229 15.71 0.000 .2202519 .2830671
L1. | -.1875781 .0150935 -12.43 0.000 -.2171641 -.1579921
lnfinafee |
--. | .0798259 .0073152 10.91 0.000 .0654868 .0941649
L1. | -.0255605 .0074199 -3.44 0.001 -.0401049 -.0110161
lnsale |
--. | .1703522 .015042 11.33 0.000 .1408672 .1998372
L1. | -.0594901 .0154663 -3.85 0.000 -.0898066 -.0291735
_cons | .1174737 .0434328 2.70 0.007 .0323379 .2026095
------------------------------------------------------------------------------
Instruments for first differences equation
Standard
D.(L2.lntotdebt lnprofit L.lnprofit L2.lnprofit lnasset L.lnasset
L2.lnasset lnfinafee L.lnfinafee L2.lnfinafee lnsale L.lnsale L2.lnsale)
GMM-type (missing=0, separate instruments for each period unless collapsed)
L(1/.).L.lntotdebt
Instruments for levels equation
Standard
_cons
L2.lntotdebt lnprofit L.lnprofit L2.lnprofit lnasset L.lnasset L2.lnasset
lnfinafee L.lnfinafee L2.lnfinafee lnsale L.lnsale L2.lnsale
GMM-type (missing=0, separate instruments for each period unless collapsed)
D.L.lntotdebt
------------------------------------------------------------------------------
Arellano-Bond test for AR(1) in first differences: z = -12.79 Pr > z = 0.000
Arellano-Bond test for AR(2) in first differences: z = 2.68 Pr > z = 0.007
------------------------------------------------------------------------------
Sargan test of overid. restrictions: chi2(30) =1843.27 Prob > chi2 = 0.000
(Not robust, but not weakened by many instruments.)
Hansen test of overid. restrictions: chi2(30) = 293.75 Prob > chi2 = 0.000
(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(24) = 146.75 Prob > chi2 = 0.000
Difference (null H = exogenous): chi2(6) = 147.00 Prob > chi2 = 0.000
gmm(L.lntotdebt, lag(1 .))
Hansen test excluding group: chi2(4) = 10.05 Prob > chi2 = 0.040
Difference (null H = exogenous): chi2(26) = 283.69 Prob > chi2 = 0.000
iv(L2.lntotdebt lnprofit L.lnprofit L2.lnprofit lnasset L.lnasset L2.lnasset lnfinafee L.ln
> finafee L2.lnfinafee lnsale L.lnsale L2.lnsale)
Hansen test excluding group: chi2(17) = 66.18 Prob > chi2 = 0.000
Difference (null H = exogenous): chi2(13) = 227.57 Prob > chi2 = 0.000
二阶sys-GMM模型
. do "C:\DOCUME~1\ADMINI~1\LOCALS~1\Temp\STD0b000000.tmp"
. xtabond2 lntotdebt L.lntotdebt L(0/1).(lnprofit lnasset lnfinafee lnsale),gmmstyle(L.lntotd
> ebt)ivstyle(L2.lntotdebt L(0/2).(lnprofit lnasset lnfinafee lnsale))robust twostep small
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: i Number of obs = 23792
Time variable : year Number of groups = 11304
Number of instruments = 40 Obs per group: min = 0
F(9, 11303) = 13197.74 avg = 2.10
Prob > F = 0.000 max = 6
------------------------------------------------------------------------------
| Corrected
lntotdebt | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
lntotdebt |
L1. | .8580987 .0075922 113.02 0.000 .8432166 .8729807
lnprofit |
--. | -.0290653 .0052277 -5.56 0.000 -.0393125 -.018818
L1. | -.0100079 .0049228 -2.03 0.042 -.0196573 -.0003584
lnasset |
--. | .2189423 .0178958 12.23 0.000 .1838634 .2540211
L1. | -.1696932 .0167577 -10.13 0.000 -.2025413 -.1368451
lnfinafee |
--. | .0686537 .0077542 8.85 0.000 .0534541 .0838533
L1. | -.0307917 .007787 -3.95 0.000 -.0460556 -.0155279
lnsale |
--. | .1547309 .0162162 9.54 0.000 .1229443 .1865175
L1. | -.068233 .0167725 -4.07 0.000 -.10111 -.035356
_cons | .0942985 .0448498 2.10 0.036 .0063851 .1822119
------------------------------------------------------------------------------
Instruments for first differences equation
Standard
D.(L2.lntotdebt lnprofit L.lnprofit L2.lnprofit lnasset L.lnasset
L2.lnasset lnfinafee L.lnfinafee L2.lnfinafee lnsale L.lnsale L2.lnsale)
GMM-type (missing=0, separate instruments for each period unless collapsed)
L(1/.).L.lntotdebt
Instruments for levels equation
Standard
_cons
L2.lntotdebt lnprofit L.lnprofit L2.lnprofit lnasset L.lnasset L2.lnasset
lnfinafee L.lnfinafee L2.lnfinafee lnsale L.lnsale L2.lnsale
GMM-type (missing=0, separate instruments for each period unless collapsed)
D.L.lntotdebt
------------------------------------------------------------------------------
Arellano-Bond test for AR(1) in first differences: z = -12.57 Pr > z = 0.000
Arellano-Bond test for AR(2) in first differences: z = 2.77 Pr > z = 0.006
------------------------------------------------------------------------------
Sargan test of overid. restrictions: chi2(30) =1843.27 Prob > chi2 = 0.000
(Not robust, but not weakened by many instruments.)
Hansen test of overid. restrictions: chi2(30) = 293.75 Prob > chi2 = 0.000
(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(24) = 146.75 Prob > chi2 = 0.000
Difference (null H = exogenous): chi2(6) = 147.00 Prob > chi2 = 0.000
gmm(L.lntotdebt, lag(1 .))
Hansen test excluding group: chi2(4) = 10.05 Prob > chi2 = 0.040
Difference (null H = exogenous): chi2(26) = 283.69 Prob > chi2 = 0.000
iv(L2.lntotdebt lnprofit L.lnprofit L2.lnprofit lnasset L.lnasset L2.lnasset lnfinafee L.ln
> finafee L2.lnfinafee lnsale L.lnsale L2.lnsale)
Hansen test excluding group: chi2(17) = 66.18 Prob > chi2 = 0.000
Difference (null H = exogenous): chi2(13) = 227.57 Prob > chi2 = 0.000
这样的结果是否表明工具变量的选择有问题,是否应该更换工具变量?急急急!!!