DPD:Sargan和Hansen检验矛盾怎么办-经管之家官网！

免费学术公开课,扫码加入

检验过度识别约束，xtabond2里面sargan and hansen检验老是矛盾，问题到底出在哪里啊？下面用例子说明：

第一个模型不进行标准差调整，第二个模型进行调整。两个模型中sargan and hansen检验结果都矛盾。我做了其他的手册上的模型，发现这是一个普遍问题。一直没有想通。相关性检验又没有什么问题，而且这个例子是David Roodman最后给出的例子，复制DPD for OX中对应的结果。

请高手指点一下，谢谢！

1. 没有放robust

use http://www.stata-press.com/data/r7/abdata.dta
. xtabond2 n l.n l(0/1).(w k) yr1978-yr1984, gmm(L.(w k n)) iv(yr1978-yr1984, eq(lev
> el)) h(2) two small
Dynamic panel-data estimation, two-step system GMM
------------------------------------------------------------------------------
n | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
n |
L1. | .872881 .0067325 129.65 0.000 .8595697 .8861923
w |
--. | -.7797449 .0087665 -88.95 0.000 -.7970779 -.7624119
L1. | .5268032 .0145408 36.23 0.000 .4980536 .5555529
k |
--. | .4700773 .0144778 32.47 0.000 .4414521 .4987024
L1. | -.3576081 .014154 -25.27 0.000 -.3855931 -.3296232
yr1978 | .0058018 .0055501 1.05 0.298 -.0051717 .0167753
yr1979 | .0188977 .0054704 3.45 0.001 .0080817 .0297137
yr1980 | .0028196 .0054678 0.52 0.607 -.0079911 .0136304
yr1981 | -.0200226 .0065488 -3.06 0.003 -.0329708 -.0070744
yr1982 | .0152802 .0047388 3.22 0.002 .0059107 .0246498
yr1983 | .031731 .0053602 5.92 0.000 .0211329 .0423291
yr1984 | .0224206 .0049654 4.52 0.000 .012603 .0322381
_cons | .9484881 .0626819 15.13 0.000 .8245548 1.072421
------------------------------------------------------------------------------
Warning: Uncorrected two-step standard errors are unreliable.
------------------------------------------------------------------------------
Arellano-Bond test for AR(1) in first differences: z = -6.30 Pr > z = 0.000
Arellano-Bond test for AR(2) in first differences: z = -0.15 Pr > z = 0.881
------------------------------------------------------------------------------
Sargan test of overid. restrictions: chi2(100) = 186.75 Prob > chi2 = 0.000

Hansen test of overid. restrictions: chi2(100) = 111.59 Prob > chi2 = 0.201

2.放robust

. xtabond2 n l.n l(0/1).(w k) yr1978-yr1984, gmm(L.(w k n)) iv(yr1978-yr1984, eq(lev
> el)) h(2) two small robust
Dynamic panel-data estimation, two-step system GMM
------------------------------------------------------------------------------
| Corrected
n | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
n |
L1. | .872881 .0457559 19.08 0.000 .7824136 .9633485
w |
--. | -.7797449 .1177744 -6.62 0.000 -1.012606 -.5468839
L1. | .5268032 .1637713 3.22 0.002 .2029983 .8506082
k |
--. | .4700773 .0806911 5.83 0.000 .3105366 .6296179
L1. | -.3576081 .0808642 -4.42 0.000 -.5174911 -.1977251
yr1978 | .0058018 .0199152 0.29 0.771 -.0335741 .0451777
yr1979 | .0188977 .0230045 0.82 0.413 -.0265862 .0643816
yr1980 | .0028196 .0243216 0.12 0.908 -.0452685 .0509078
yr1981 | -.0200226 .0277278 -0.72 0.471 -.0748454 .0348002
yr1982 | .0152802 .0235491 0.65 0.517 -.0312804 .0618409
yr1983 | .031731 .0237422 1.34 0.184 -.0152116 .0786736
yr1984 | .0224206 .031398 0.71 0.476 -.0396589 .0845001
_cons | .9484881 .3814834 2.49 0.014 .1942277 1.702749
------------------------------------------------------------------------------

------------------------------------------------------------------------------
Arellano-Bond test for AR(1) in first differences: z = -5.81 Pr > z = 0.000
Arellano-Bond test for AR(2) in first differences: z = -0.15 Pr > z = 0.883
------------------------------------------------------------------------------
Sargan test of overid. restrictions: chi2(100) = 186.75 Prob > chi2 = 0.000

Hansen test of overid. restrictions: chi2(100) = 111.59 Prob > chi2 = 0.201

Roodman的working paper见下面第2楼：

http://www.pinggu.org/bbs/thread-349848-1-1.html

「经管之家」APP：经管人学习、答疑、交友，就上经管之家！
免流量费下载资料----在经管之家app可以下载论坛上的所有资源，并且不额外收取下载高峰期的论坛币。
涵盖所有经管领域的优秀内容----覆盖经济、管理、金融投资、计量统计、数据分析、国贸、财会等专业的学习宝库，各类资料应有尽有。
来自五湖四海的经管达人----已经有上千万的经管人来到这里，你可以找到任何学科方向、有共同话题的朋友。
经管之家（原人大经济论坛），跨越高校的围墙，带你走进经管知识的新世界。
扫描下方二维码下载并注册APP