请教STATA动态回归结果解释?

是 否 +2 论坛币

k人 参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

用STATA8.0里面的xtabond命令做动态回归，回归结果里面一些统计量不知道是什么意思，请教一下

Sargan test of over-identifying restrictions:

chi2(305) = 11.21 Prob > chi2 = 1.0000

Arellano-Bond test that average autocovariance in residuals of order 1 is 0:

H0: no autocorrelation z = -0.62 Pr > z = 0.5382

Arellano-Bond test that average autocovariance in residuals of order 2 is 0:

H0: no autocorrelation z = -0.94 Pr > z = 0.3471

谢谢！

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

分享0 收藏1 回帖

关键词：Stata 回归结果 动态回归 tata 结果解释 请教 解释 结果 Stata 动态

顶一下，谢谢１

sargen test 为工具变量的有效性检验

sargan test 服从卡方分布，它的统计量不能太大，你的结果明显reject掉了你的工具变量的有效性

至于Arellano-Bond test ，check一下，arellano和bond （1991）年的paper吧

印象中，residual应该是ar（1）的

谢谢楼上两位，再问一下如果结果reject了工具变量的有效性是不是回归的结果就不可信了？还是有什么其它影响，要怎么处理呢？谢谢！

根据你的假设和数据试试其他的设定，stata的xtabond命令提供了很大灵活性

嗯，不错

1. The Sargan test of overidentifying restrictions, used to examine the overall validity of the instruments by comparing the moment conditions with their sample analogue.It is a good news when p-value is large (better not close to 1) - means Sargan test can not be rejested and therefore instruments are valid.But you have pvalue=1, which implies that something is going wrong in your regression.

2/3.The first-order/second-order serial correlation tests, which test the null hypothesis of no first-order serial correlation and no second-order serial correlation in the residuals in the first-differenced equation. Therefore it is a good news if you get small p-value (to rejest the null) for 1st serial correlation test, but large p-value for 2nd serial correlation test. You have large p-value (0.5382) for 1st serial correlation test, obviously this is wrong. You could consider including more lags, then the problem can be solved. Hope these help!

如何消除sargan检验中 p value=1?