谢谢大家。我看了“Testing Exogeneity in the Bivariate Probit Model:AMonte Carlo Study ”这篇文章，正在用biprobit命令做双变量probit模型的内生性检验方法的比较，做到Wald检验的时候，需要用到rho的标准差，具体见下图。看到结果里面有出现它，但是发现好像只储存e(rho),然后variance-covariance matrix of the estimators也就是e(V)也只存了athrho的方差。请问要如何提取出来？或者有其他方法做wald检验吗？

再次感谢！

用到过的命令和结果如下：

biprobit (y1=x z)(y2=y1 t z)

Seeminglyunrelated bivariate probit Number of obs = 500

Wald chi2(5) = 230.46

Log likelihood =-235.73715 Prob> chi2 = 0.0000

------------------------------------------------------------------------------

| Coef.Std. Err. z P>|z| [95% Conf. Interval]

-------------+----------------------------------------------------------------

y1 |

x |1.233294 .1525567 8.080.000 .9342885 1.5323

z |2.134341 .2032282 10.500.000 1.736021 2.532661

_cons |.7412778 .1093811 6.780.000 .5268948 .9556607

-------------+----------------------------------------------------------------

y2 |

y1 |.4698437 .3130575 1.500.133 -.1437379 1.083425

t |.6021803 .3341506 1.800.072 -.0527429 1.257103

z |1.440157 .2681947 5.370.000 .9145054 1.965809

_cons |-.056587 .2328025 -0.240.808 -.5128716 .3996976

-------------+----------------------------------------------------------------

/athrho |.8361529 .2872247 2.910.004 .2732029 1.399103

-------------+----------------------------------------------------------------

rho | .683766 .1529368 .2666026 .8851576

------------------------------------------------------------------------------

Likelihood-ratiotest of rho=0: chi2(1) =9.50153 Prob > chi2 = 0.0021

mat SE=e(V)

mat list e(V)