做了一个IV-2SLS,我的疑问是:
1,过度识别这个应该是说明,至少有一个变量不是外生的。对吗?我如何知道还有哪一个变量不是外生的,用什么方法呢?
2,弱工具变量检验,我只知道Minimum eigenvalue statistic(最小特征值统计量),应该大于10。下面偏相关的部分什么意思呢?
求高人点拨!点拨一次胜造七级浮屠啊,呵呵,感谢!
命令如下:
ivregress 2sls lnwage distance district cityD exper exper2 age age2 minzu workT training workF marriage gender (occupa2 occupa3= edu2 edu3 industry2 industry3 industry4 industry5 industry6 empWay2 empWay3 property2 property3 labour population ),first
estat firststage,all forcenonrobust
工具变量检验得出如下结果:
First-stage regression summary statistics
--------------------------------------------------------------------------
| Adjusted Partial
Variable | R-sq. R-sq. R-sq. F(13,40617) Prob > F
-------------+------------------------------------------------------------
occupa2 | 0.6384 0.6382 0.1376 498.457 0.0000
occupa3 | 0.6231 0.6228 0.1338 482.745 0.0000
--------------------------------------------------------------------------
Shea's partial R-squared
--------------------------------------------------
| Shea's Shea's
Variable | Partial R-sq. Adj. Partial R-sq.
-------------+------------------------------------
occupa2 | 0.0688 0.0682
occupa3 | 0.0669 0.0664
--------------------------------------------------
Minimum eigenvalue statistic = 224.124
Critical Values # of endogenous regressors: 2
Ho: Instruments are weak # of excluded instruments: 13
---------------------------------------------------------------------
| 5% 10% 20% 30%
2SLS relative bias | 19.64 10.84 6.21 4.56
-----------------------------------+---------------------------------
| 10% 15% 20% 25%
2SLS Size of nominal 5% Wald test | 34.62 18.84 13.45 10.68
LIML Size of nominal 5% Wald test | 3.56 2.48 2.17 2.02
---------------------------------------------------------------------
过度识别检验得出结果如下:
estat overid
Tests of overidentifying restrictions:
Sargan (score) chi2(11)= 1122.82 (p = 0.0000)
Basmann chi2(11) = 1153.96 (p = 0.0000)


雷达卡





京公网安备 11010802022788号







