if you want to do marginal effects for multivariate probit models in stata, it is best to download the user written program 'cmp' by Roodman. The mvpobrit model in stata doesn't have a post estimation command that allows for the calculation of average marginal effects. It is possible to do the marginal effects, but it will be a fairly long process.

I tend to take the easy route and stick to CMP. It is great, as it is much more general than the mvprobit command as you can do "Conditional mixed process" models of many different types, not simply multivariate probit models, Stephen Jenkins (one of the creators of the mvprobit command for stata) even recommends it for calculating average marginal effects ! You may have to read a bit (like the help files) but it is quite easy once you get the hang...though sometimes, it does take a bit long to estimate the models

Also, if you are familar with R, you can use mprobit command in R. This is pretty cool. It lets you do marginal effects for both the conditional and unconditional probabilities!

Hey Mahalia, thank you very much. I will surely go through it. 

But please remember that cmp does NOT give you marginal effect after multivariate probit if you have more than two equations, there is no easy way around this as far as I know. You will have to do it by hand!

So Taj, Have you tried this command.

I also need help to do post estimation marginal effect after multivariate probit. 

Dear All,

I have worked on this and written codes below for estimating marginal effect after MVPROBIT. I hope this will be useful. *Example data use http://www.stata-press.com/data/r7/school.dta, clear *Step 1: Running the MV probit model mvprobit (private = years logptax loginc) (vote = years logptax loginc)

*Step 2: Post estimation command to estimate Predictions from multivariate probit models estimated by SML mvppred pred_xb, xb *Step 3" Generate coeefiencts for each binay category gen Coef_years_private = -.0089447 gen Coef_logptax_private =-.1018381 gen Coef_loginc_private =.3787381 gen Coef_years_vote = -.0160871 gen Coef_logptax_vote =-1.260877 gen Coef_loginc_vote =.9744685 *Step 4: Calculating Marginal effect using (Coefficients and linear Predictions) gen ME_years_private =normalden(pred_xb1)*Coef_years_private gen ME_logpatx_private =normalden(pred_xb1)*Coef_logptax_private gen ME_loginc_private =normalden(pred_xb1)*Coef_loginc_private gen ME_years_vote =normalden(pred_xb1)*Coef_years_vote gen ME_logpatx_vote =normalden(pred_xb1)*Coef_logptax_vote gen ME_loginc_vote =normalden(pred_xb1)*Coef_loginc_vote *Step 5 After estimating the ME for each observation we can get the mean using the summarize or mean command.

Thank you very much for this great informationTajuddin.

Mr. Md. Tajuddin Khan, to use multivariate probit model, we must have more than two dependent variables. So, you mean that it can be extended for three or more?