Marginsplot Predicted Probabillity Bar Graph

[Roman Johnson]

Does know how to perform a marginsplot to predict the probability of two categorical variables (e.g. a binary variable and a factor variable)?

[Marcos Almeida]

You may type:

marginsplot, recast(bar)

Hopefully that helps.

[Roman Johnson]

Thanks, Marcos.

[Roman Johnson]

Thanks. I was trying to make a predicted margins bar graph predicted the odds of mammogram for individuals with low trust and I wanted to put it all on the same graph. I entered this:

logit mammogramadherent i.race_r i.age i.education2 i.employment c.income i.family i.married i.citizenship i.obesity i.insurance i.provider i.safety i.trust i.placeofresidence i.produce i.racerxsafety i.racerxtrust i.racerxproduce
estimates store blm

estimates restore blm

margins, at(race_r == 0 trust= 1) vsquish

margins, at(race_r == 1 trust= 1) vsquish

margins, at(race_r == 3 trust= 1) vsquish

marginsplot, recast(bar) plotopts(barw(.8))


but I got the following thing (graph attached). How can I make the different racial categories show?

[Marcos Almeida]

You may use - margins race - first.