Dear Montu,

I hope it will be helpful for u. Use the command as it is only by change your dependent and independent variables.

* Bivariate probit model

biprobit $y1list $y2list $xlist

* Predicted marginal probabilities of y1=1 and y2=1

predict biprob1, pmarg1

predict biprob2, pmarg2

* Predicted joint probabilities of y1=0 and y2=0, y1=0 and y2=1, y1=1 and y2=0, and y1=1 and y2=1

predict biprob00, p00

predict biprob01, p01

predict biprob10, p10

predict biprob11, p11

* Summarizing predicted values

summarize $y1list $y2list biprob1 biprob2

summarize biprob00 biprob01 biprob10 biprob11

tabulate $y1list $y2list

* Marginal effects

margins, dydx(*) atmeans predict(p00)

margins, dydx(*) atmeans predict(p01)

margins, dydx(*) atmeans predict(p10)

margins, dydx(*) atmeans predict(p11)

* Bivariate probit with different sets of regressors

biprobit ($y1list = $zlist) ($y2list = $xlist)

Thank you so much for your response. However, I am getting some comments like this during marginal effects calculation -

margins, dydx(*) atmeans predict(p00)

prediction is a function of possibly stochastic quantities other than e(b)

r(498);

Could you please also help me to check the reliability of the predicted model?

Regards,

Montu Bose

I concur with Montu..

margins, dydx(*) atmeans predict(p00)

Basically, the problem would be solved if we use the below command -

margins, dydx(*) predict(p10) force

Recently, I have calculated few marginal effects using this command.

//Biprobit

margins, predict(pcond1) dydx(*) atmeans post

margins, predict(pcond2) dydx(*) atmeans post

//Recursive Biprobit

//Direct effect marginal

margins, predict(pmarg2) dydx(*) force post

//Direct and Indirect marginal effect (Pov equation)

margins, predict(pmarg1) dydx(*) force post

margins, predict(pcond1)dydx(*) force post

Do these make sens?