how to get marginal effects of mlogit for each category?

[Ali Sakhi]

Hello respected members

I have recently started using stata as a 1st year ECON student. I am replicating a paper where it is using mlogit as the dependent variable is categorical (1=employed, 2= working from home, 3=working aways from home),but when i just run the mlogit and then mfx, i don't get the coefficients for all the categories separately. Do I run separate mlogit for each category? The marginal effects in the paper are displayed for each individual category mentioned above, so basically how do i get that as well?

[Clyde Schechter]

Unless you are using an ancient version of Stata, the -margins- command will give you what you need. Note that depending on which version of Stata you are using, you might need to specify that you want the output for all of the levels of the outcome variable, or you might get that by default. See -help mlogit postestimation- and then select -margins- for details. But something like this excerpt:

Compute the average marginal effect of each regressor on the probability of each of the outcomes 1-3
. margins, dydx(*) predict(outcome(1)) predict(outcome(2)) predict(outcome(3))