命令为 xi:xtivreg2 AB (lnLi= l.lnLi l2.lnLi) lnTotalAssets1 lnCash1 lnTop3Salary1 ROA TDR Shrcr1 Outdir Both1 i.Year i.ind if Stock type1==1 ,fe robust endog(lnLi)
其中AB是被解释变量 lnLi是核心解释变量,Endogeneity test检验结果 P=0.4586 不显著,所以不存在内生性。但是本回归中核心解释变量lnLi的系数回归结果不显著,这种结果能用吗? 这种情况 可以认为不存在内生性,然后进行下一步实证研究操作吗?
Estimates efficient for homoskedasticity only
Statistics robust to heteroskedasticity
Number of obs = 2404
F( 10, 1192) = 22.04
Prob > F = 0.0000
Total (centered) SS = 46.3008953 Centered R2 = 0.3421
Total (uncentered) SS = 46.3008953 Uncentered R2 = 0.3421
Residual SS = 30.46194136 Root MSE = .1592
--------------------------------------------------------------------------------
| Robust
AB | Coefficient std. err. z P>|z| [95% conf. interval]
---------------+----------------------------------------------------------------
lnLi | .2972997 .5390838 0.55 0.581 -.7592852 1.353885
lnTotalAssets1 | .6085523 .0609942 9.98 0.000 .4890059 .7280986
lnCash1 | .0095059 .0184997 0.51 0.607 -.0267529 .0457646
lnTop3Salary1 | .1285047 .0265334 4.84 0.000 .0765003 .1805092
ROA | .753135 .1947199 3.87 0.000 .3714909 1.134779
TDR | -.1101093 .1535002 -0.72 0.473 -.4109642 .1907457
Shrcr1 | -.0039142 .0036537 -1.07 0.284 -.0110754 .003247
Outdir | .2334537 .2351206 0.99 0.321 -.2273743 .6942817
Both1 | .0078852 .0300483 0.26 0.793 -.0510083 .0667787
_IYear_2021 | .0441083 .0173913 2.54 0.011 .010022 .0781946
--------------------------------------------------------------------------------
Underidentification test (Kleibergen-Paap rk LM statistic): 41.731
Chi-sq(2) P-val = 0.0000
------------------------------------------------------------------------------
Weak identification test (Cragg-Donald Wald F statistic): 18.259
(Kleibergen-Paap rk Wald F statistic): 5.084
Stock-Yogo weak ID test critical values: 10% maximal IV size 19.93
15% maximal IV size 11.59
20% maximal IV size 8.75
25% maximal IV size 7.25
Source: Stock-Yogo (2005). Reproduced by permission.
NB: Critical values are for Cragg-Donald F statistic and i.i.d. errors.
------------------------------------------------------------------------------
Hansen J statistic (overidentification test of all instruments): 0.003
Chi-sq(1) P-val = 0.9567
-endog- option:
Endogeneity test of endogenous regressors: 0.549
Chi-sq(1) P-val = 0.4586
Regressors tested: lnLi
------------------------------------------------------------------------------
Instrumented: lnLi
Included instruments: lnTotalAssets1 lnCash1 lnTop3Salary1 ROA TDR Shrcr1 Outdir
Both1 _IYear_2021
Excluded instruments: L.lnLi L2.lnLi
Dropped collinear: _IYear_2020 _IYear_2022 _Iind_2 _Iind_3 _Iind_4 _Iind_5
_Iind_6 _Iind_7 _Iind_8 _Iind_9 _Iind_10 _Iind_11 _Iind_12
_Iind_13 _Iind_14 _Iind_15 _Iind_16 _Iind_17 _Iind_18
_Iind_19 _Iind_20 _Iind_21
------------------------------------------------------------------------------