[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
st: mprobit simulation
I think this didn't get sent out so let me send it again.
I am running a multinomial probit where I have 3 sectors an individual can
choose from and my key independent variable is enforcement. I run the
multinomial probit like this: mprobit sector enforcement, cluster(id)
Now I would like to conduct a policy experiment where I vary the levels of
enforcement to see how the predicted sectoral probabilities change. I do
not want to re-estimated the model. I want to use the estimated
coefficients to then answer questions like: If I change enforcement of all
women to zero (and keep all other vars the same), how does the sectoral
decision change. Any thoughts on how to esimate that?
Thanks in advance!
* For searches and help try: