发帖
雷达卡
//数据：
use https://www3.nd.edu/~rwilliam/statafiles/wages, clear
//命令1：
xtabond2 wks exp ed if south==1,gmm(wks,lag(2 .)collapse) iv(ed exp) twostep robust
//命令2：
keep if south==1
xtabond2 wks exp ed ,gmm(wks,lag(2 .)collapse) iv(ed exp) twostep robust
//结果1：
. use https://www3.nd.edu/~rwilliam/statafiles/wages, clear
. xtabond2 wks exp ed if south==1,gmm(wks,lag(2 .)collapse) iv(ed exp) twostep
> robust
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: id Number of obs = 1209
Time variable : t Number of groups = 182
Number of instruments = 9 Obs per group: min = 1
Wald chi2(2) = 34717.51 avg = 6.64
Prob > chi2 = 0.000 max = 7
------------------------------------------------------------------------------
| Corrected
wks | Coefficient std. err. z P>|z| [95% conf. interval]
-------------+----------------------------------------------------------------
exp | -.0477394 .0265605 -1.80 0.072 -.099797 .0043183
ed | -.0313986 .1024907 -0.31 0.759 -.2322768 .1694795
_cons | 48.58417 1.542108 31.51 0.000 45.56169 51.60665
------------------------------------------------------------------------------
Instruments for first differences equation
Standard
D.(ed exp)
GMM-type (missing=0, separate instruments for each period unless collapsed)
L(2/6).wks collapsed
Instruments for levels equation
Standard
ed exp
_cons
GMM-type (missing=0, separate instruments for each period unless collapsed)
DL.wks collapsed
------------------------------------------------------------------------------
Arellano-Bond test for AR(1) in first differences: z = -3.50 Pr > z = 0.000
Arellano-Bond test for AR(2) in first differences: z = -1.61 Pr > z = 0.108
------------------------------------------------------------------------------
Sargan test of overid. restrictions: chi2(6) = 64.92 Prob > chi2 = 0.000
(Not robust, but not weakened by many instruments.)
Hansen test of overid. restrictions: chi2(6) = 15.96 Prob > chi2 = 0.014
(Robust, but weakened by many instruments.)
Difference-in-Hansen tests of exogeneity of instrument subsets:
GMM instruments for levels
Hansen test excluding group: chi2(5) = 14.85 Prob > chi2 = 0.011
Difference (null H = exogenous): chi2(1) = 1.11 Prob > chi2 = 0.293
gmm(wks, collapse lag(2 .))
Hansen test excluding group: chi2(0) = 0.00 Prob > chi2 = .
Difference (null H = exogenous): chi2(6) = 15.96 Prob > chi2 = 0.014
iv(ed exp)
Hansen test excluding group: chi2(4) = 2.49 Prob > chi2 = 0.647
Difference (null H = exogenous): chi2(2) = 13.47 Prob > chi2 = 0.001
//结果2：
. use https://www3.nd.edu/~rwilliam/statafiles/wages, clear
.
. keep if south==1
(2,956 observations deleted)
. xtabond2 wks exp ed ,gmm(wks,lag(2 .)collapse) iv(ed exp) twostep robust
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: id Number of obs = 1209
Time variable : t Number of groups = 182
Number of instruments = 9 Obs per group: min = 1
Wald chi2(2) = 34718.00 avg = 6.64
Prob > chi2 = 0.000 max = 7
------------------------------------------------------------------------------
| Corrected
wks | Coefficient std. err. z P>|z| [95% conf. interval]
-------------+----------------------------------------------------------------
exp | -.0469161 .0267252 -1.76 0.079 -.0992966 .0054644
ed | -.0306545 .1024905 -0.30 0.765 -.2315321 .1702232
_cons | 48.5599 1.543044 31.47 0.000 45.53559 51.58421
------------------------------------------------------------------------------
Instruments for first differences equation
Standard
D.(ed exp)
GMM-type (missing=0, separate instruments for each period unless collapsed)
L(2/6).wks collapsed
Instruments for levels equation
Standard
ed exp
_cons
GMM-type (missing=0, separate instruments for each period unless collapsed)
DL.wks collapsed
------------------------------------------------------------------------------
Arellano-Bond test for AR(1) in first differences: z = -3.47 Pr > z = 0.001
Arellano-Bond test for AR(2) in first differences: z = -1.62 Pr > z = 0.105
------------------------------------------------------------------------------
Sargan test of overid. restrictions: chi2(6) = 66.07 Prob > chi2 = 0.000
(Not robust, but not weakened by many instruments.)
Hansen test of overid. restrictions: chi2(6) = 15.87 Prob > chi2 = 0.014
(Robust, but weakened by many instruments.)
Difference-in-Hansen tests of exogeneity of instrument subsets:
GMM instruments for levels
Hansen test excluding group: chi2(5) = 14.68 Prob > chi2 = 0.012
Difference (null H = exogenous): chi2(1) = 1.20 Prob > chi2 = 0.274
gmm(wks, collapse lag(2 .))
Hansen test excluding group: chi2(0) = 0.00 Prob > chi2 = .
Difference (null H = exogenous): chi2(6) = 15.87 Prob > chi2 = 0.014
iv(ed exp)
Hansen test excluding group: chi2(4) = 2.41 Prob > chi2 = 0.661
Difference (null H = exogenous): chi2(2) = 13.46 Prob > chi2 = 0.001
在小样本中结果差别不大，但在大样本中这种差别就没办法忽视了，尤其是解释变量是类似基尼系数这种介于0-1之间的话
京公网安备 11010802022788号
