最近写论文需要用stata分析,但是专业原因没有学过stata,这几天在网上做了很多功课,也看了这方面的书籍,实践起来还是有问题。想请问,在oprobit分析后求边际效应应该是输入怎样 的命令呢?这是我的oprobit分析:
Ordered probit regression Number of obs = 164
LR chi2(4) = 33.17
Prob > chi2 = 0.0000
Log likelihood = -185.84233 Pseudo R2 = 0.0819
------------------------------------------------------------------------------
y | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
a | .0403109 .0999715 0.40 0.687 -.1556296 .2362514
b | .216727 .1099472 1.97 0.049 .0012345 .4322194
c | .2849362 .105866 2.69 0.007 .0774426 .4924299
d | .2375953 .1073558 2.21 0.027 .0271819 .4480087
-------------+----------------------------------------------------------------
/cut1 | .6352732 .4509545 -.2485814 1.519128
/cut2 | 1.000509 .4418611 .1344775 1.866541
/cut3 | 2.264174 .4586265 1.365283 3.163066
/cut4 | 3.979804 .5103473 2.979542 4.980066
------------------------------------------------------------------------------
然后我输入了margins,dydx(*),得到:
Average marginal effects Number of obs = 164
Model VCE : OIM
Expression : Pr(y==1), predict()
dy/dx w.r.t. : a b c d
------------------------------------------------------------------------------
| Delta-method
| dy/dx Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
a | -.0038695 .0097372 -0.40 0.691 -.022954 .015215
b | -.0208039 .0114213 -1.82 0.069 -.0431893 .0015814
c | -.0273514 .0117859 -2.32 0.020 -.0504514 -.0042515
d | -.0228071 .01173 -1.94 0.052 -.0457975 .0001833
------------------------------------------------------------------------------
由于我的变量是五点变量,所以想求y分别取1-5时的各边际效应,请问应该如何做呢? 输入 margins ,dydx at(y=1)后显示'y' not found in list of covariates
谢谢大家!!救救我吧