发帖
雷达卡
. xtabond TobinQ_A_1 INDEPENDENCE_1 BOARD_NUM_LN_1 DUAL_1 ControlProportion_1 SHAREHOLDERS_LN_1 SEO_1 WOMEN_CEO EMPLOYEE_LN_1 LEVERAGE_1 AGE_LN_1,lags(2) maxldep(3) endogenous(_WOMEN_1,lag(0,2)) twostep vce(robust)
Arellano-Bond dynamic panel-data estimation Number of obs = 5,175
Group variable: id Number of groups = 1,160
Time variable: Year
Obs per group:
min = 1
avg = 4.461207
max = 11
Number of instruments = 65 Wald chi2(13) = 106.60
Prob > chi2 = 0.0000
Two-step results
(Std. Err. adjusted for clustering on id)
-------------------------------------------------------------------------------------
| WC-Robust
TobinQ_A_1 | Coef. Std. Err. z P>|z| [95% Conf. Interval]
--------------------+----------------------------------------------------------------
TobinQ_A_1 |
L1. | -.2466403 .0536139 -4.60 0.000 -.3517216 -.1415589
L2. | -.1691084 .0329235 -5.14 0.000 -.2336372 -.1045796
|
_WOMEN_1 | -9.328174 2.99109 -3.12 0.002 -15.1906 -3.465745
INDEPENDENCE_1 | .9803128 1.520862 0.64 0.519 -2.000521 3.961147
BOARD_NUM_LN_1 | -.6164094 .5990199 -1.03 0.303 -1.790467 .557648
DUAL_1 | .131173 .1603955 0.82 0.413 -.1831964 .4455424
ControlProportion_1 | -.0052318 .0065971 -0.79 0.428 -.0181618 .0076982
SHAREHOLDERS_LN_1 | .5197102 .1049699 4.95 0.000 .313973 .7254475
SEO_1 | .3311272 .0877823 3.77 0.000 .1590769 .5031774
WOMEN_CEO | .4483457 .3955307 1.13 0.257 -.3268803 1.223572
EMPLOYEE_LN_1 | -.4982794 .1817091 -2.74 0.006 -.8544227 -.1421362
LEVERAGE_1 | -.2656784 .6142671 -0.43 0.665 -1.46962 .938263
AGE_LN_1 | .6760216 .1866836 3.62 0.000 .3101284 1.041915
_cons | 2.764657 2.468318 1.12 0.263 -2.073158 7.602471
-------------------------------------------------------------------------------------
Instruments for differenced equation
GMM-type: L(2/4).TobinQ_A_1 L(2/3)._WOMEN_1
Standard: D.INDEPENDENCE_1 D.BOARD_NUM_LN_1 D.DUAL_1 D.ControlProportion_1
D.SHAREHOLDERS_LN_1 D.SEO_1 D.WOMEN_CEO D.EMPLOYEE_LN_1
D.LEVERAGE_1 D.AGE_LN_1
Instruments for level equation
Standard: _cons
. estat abond
Arellano-Bond test for zero autocorrelation in first-differenced errors
+-----------------------+
|Order | z Prob > z|
|------+----------------|
| 1 |-4.7896 0.0000 |
| 2 |-.92447 0.3552 |
+-----------------------+
H0: no autocorrelation
.
end of do-file
. do "E:\STATA14\STD04000000.tmp"
. quietly xtabond TobinQ_A_1 INDEPENDENCE_1 BOARD_NUM_LN_1 DUAL_1 ControlProportion_1 SHAREHOLDERS_LN_1 SEO_1 WOMEN_CEO EMPLOYEE_LN_1 LEVERAGE_1 AGE
> _LN_1,lags(2) maxldep(3) endogenous(_WOMEN_1,lag(0,2)) twostep
. estat sargan
Sargan test of overidentifying restrictions
H0: overidentifying restrictions are valid
chi2(51) = 369.3795
Prob > chi2 = 0.0000
.
end of do-file
. do "E:\STATA14\STD04000000.tmp"
. est store DiffGMM2
.
end of do-file
. do "E:\STATA14\STD04000000.tmp"
. esttab DiffGMM2, b(%6.4f) star (* 0.1 ** 0.05 *** 0.01)
----------------------------
(1)
TobinQ_A_1
----------------------------
L.TobinQ_A_1 -0.2466***
(-10.97)
L2.TobinQ_~1 -0.1691***
(-10.44)
_WOMEN_1 -9.3282***
(-5.97)
INDEPENDEN~1 0.9803
(0.96)
BOARD_NUM_~1 -0.6164
(-1.64)
DUAL_1 0.1312
(1.25)
ControlPro~1 -0.0052
(-1.16)
SHAREHOLDE~1 0.5197***
(7.50)
SEO_1 0.3311***
(5.52)
WOMEN_CEO 0.4483*
(1.89)
EMPLOYEE_L~1 -0.4983***
(-4.16)
LEVERAGE_1 -0.2657
(-0.67)
AGE_LN_1 0.6760***
(5.71)
_cons 2.7647*
(1.79)
----------------------------
N 5175
----------------------------
t statistics in parentheses
* p<0.1, ** p<0.05, *** p<0.01
我采用差分GMM来做，_WOMEN_1内生变量，结果发现_WOMEN_1 的系数奇大无比，想知道哪里错了
京公网安备 11010802022788号
