[面板数据求助] 如何用xtabond2命令进行系统GMM估计，请请我 [推广有奖]

21楼

ywh19860616 发表于 2012-5-16 09:59:46

xx_13120 发表于 2012-5-16 09:30
但是系统GMM不是还包括水平方程吗？水平方程里的个体虚拟变量还存在啊

请仔细阅读How to do xtabond2: An introduction to difference and system GMM in Stata
page 31 / 45

一份耕耘，一份收获。

22楼

xx_13120 发表于 2012-5-16 10:10:19

ywh19860616 发表于 2012-5-16 09:59
请仔细阅读How to do xtabond2: An introduction to difference and system GMM in Stata
page 31 / 45

谢谢！但是您看这篇文章http://www.usc.cuhk.edu.hk/Paper ... es/8458_1_paper.pdf
最后还估计出了个体固定效应的系数（东部地区，西部地区）
或者这个链接http://www.google.com.hk/search? ... 0...0.0.lGnMxMv-KFw

23楼

ywh19860616 发表于 2012-5-16 10:29:22

xx_13120 发表于 2012-5-16 10:10
谢谢！但是您看这篇文章http://www.usc.cuhk.edu.hk/PaperCollection/webmanager/wkfiles/8458_1_paper.p ...

作者提到了，在SYS-GMM可以加入不随时间改变的变量，但是按照他的意思还是不要加入（比如地区虚拟变量id），尤其是T比较小时。
你提到的文章只加入了2个虚拟变量，应该影响不大。

总之，就是说，你可以加入这些虚拟变量，但是不是很提倡，尤其是只是为了起到控制作用时。

一份耕耘，一份收获。

24楼

liqiangyi 发表于 2012-5-20 19:15:30

请教各位前辈：初学stata,很多不懂，我的运行结果出现了这样的问题，如何调整啊？.
xtabond2  lnpso2 L1.lnpso2  lngdp1 lngdp2 fdi open rd cs  cy lnt ,gmm( lngdp1 lngdp2 fdi open)  iv( cy  cs rd ) sm
> all
Favoring space over speed. To switch, type or click on mata: mata set matafavor speed, perm.
Warning: Number of instruments may be large relative to number of observations.

Dynamic panel-data estimation, one-step system GMM
------------------------------------------------------------------------------
Group variable: id                            Number of obs    =    330
Time variable : year                         Number of groups =       30
Number of instruments = 262                   Obs per group: min =       11
F(9, 320)    = 619.18                                     avg =    11.00
Prob > F    =    0.000                                     max =       11
------------------------------------------------------------------------------
   lnpso2 |    Coef. Std. Err.    t P>|t|    [95% Conf. Interval]
-------------+----------------------------------------------------------------
   lnpso2 |
      L1. | .9757271 .0161126 60.56 0.000    .9440271 1.007427
   lngdp1 |  -.0228326 .0134672 -1.70 0.091 -.0493279 .0036628
   lngdp2 |  -.0044345 .0074174 -0.60 0.550 -.0190275 .0101586
      fdi | .500033 .3333576    1.50 0.135 -.1558163 1.155882
      open |  -.0096628 .0282187 -0.34 0.732 -.0651803 .0458547
      rd |  -2.713647 1.049227 -2.59 0.010 -4.777902 -.6493921
      cs |  -.0228392 .0809311 -0.28 0.778 -.1820635 .1363851
      cy | .061696 .0801163    0.77 0.442 -.0959253 .2193173
      lnt |  -.0169977 .015899 -1.07 0.286 -.0482775 .0142821
   _cons |  -.0458126 .0920646 -0.50 0.619    -.226941 .1353158
------------------------------------------------------------------------------
Instruments for first differences equation
  Standard
D.(cy cs rd)
  GMM-type (missing=0, separate instruments for each period unless collapsed)
L(1/.).(lngdp1 lngdp2 fdi open)
Instruments for levels equation
  Standard
_cons
cy cs rd
  GMM-type (missing=0, separate instruments for each period unless collapsed)
D.(lngdp1 lngdp2 fdi open)
------------------------------------------------------------------------------
Arellano-Bond test for AR(1) in first differences: z =    .  Pr > z =    .
Arellano-Bond test for AR(2) in first differences: z = 0.86  Pr > z =  0.388
------------------------------------------------------------------------------
Sargan test of overid. restrictions: chi2(252)  = 276.38  Prob > chi2 =  0.140
  (Not robust, but not weakened by many instruments.)

Difference-in-Sargan tests of exogeneity of instrument subsets:
  GMM instruments for levels
Sargan test excluding group:    chi2(214)  = 224.89  Prob > chi2 =  0.291
Difference (null H = exogenous): chi2(38) =  51.49  Prob > chi2 =  0.071
  iv(cy cs rd)
Sargan test excluding group:    chi2(249)  = 271.21  Prob > chi2 =  0.159
Difference (null H = exogenous): chi2(3) = 5.17  Prob > chi2 =  0.160

.
.
.