Hello.
I would like to to obtain the combined variance-covariance matrix from a linear regression and a probit model. However, for the latter, i would like this to refer to the marginal effect and not the original coefficient.
I have tried several combinations of margins and suest without success. For example:
Is something like this possible?
I would like to to obtain the combined variance-covariance matrix from a linear regression and a probit model. However, for the latter, i would like this to refer to the marginal effect and not the original coefficient.
I have tried several combinations of margins and suest without success. For example:
Code:
regress y1 x1 x2 x3 x4 x5 estimates store m1 probit y2 x1 x2 x3 x4 x5 margins x1 x1 x2 x3 x4 x5, post estimates store m2 suest m1 m2 y2 was estimated with a nonstandard vce r(322);
Comment