So I have three ways to estimate this:
- Multinomial logistic
- Multinomial probit (is better because I do not need the IIA property)
- Sequential probit
I was looking for the commads of these three models in Stata and I just
find de mlogist. How can I estimate multinomial probit or sequential probit
in Stata?
There might be a multinomial probit command, but if so I am not aware of
it. If it doesn't exist, it may be, because as Long (1997, p. 83) points
out, for models with nominal dependent variables that have more than 2
categories, the logit model may be preferred because the corresponding
probit model is too computationally demanding.
