Hello everyone,

I am conducting a study to analyze accident data. I have two outcome variables, namely crash severity for an aggressive driver (3 levels) and crash severity for a non-aggressive driver (3 levels). The bioprobit model simultaneously models both outcomes. For brevity, I have provided a sample of the code I used.

bioprobit (severity_aggressive = spring mainline nol3_4 ) (severity_non_aggressive= summer nomed grade )


After running the model, I want to estimate the margins for each level under both outcomes.

I have tried using mfx compute, predict(outcome(0,0)). This gives me the estimates for Pr(severity_aggressive=0, severity_aggressive=0); however, I am intersted in finding margins at each level of both outcomes, that is, only Pr(severity_aggressive=0), Pr(severity_aggressive=1), Pr(severity_aggressive=2); then Pr(severity_non_aggressive=0), Pr(severity_non_aggressive=1), Pr(severity_non_aggressive=2).

I would be very glad if someone can help me figure this out. Looking forward to hearing from you soon.

Thank you.