Thomas J. Leeper

Ooh, you're probably right. That's going to be tricky because it's hard to extract duplicate-named columns from a data frame.

Thanks. Good feedback!

This is not a supported model type currently.

Thanks - this might need to be fixed upstream in data.table but I'll investigate if there's anything we can do here. If you find a solution in the meantime, I'd...

I may solve this or I may wait to see what happens when we move plotting to ggplot. Regardless, I'll try to add tests for data.table.

Yea, this has been a problem at times. I guess it needs to be character. We should add: - [ ] Documentation of correct behavior - [ ] Some tests...

The levels are also being written as numbers rather than their labels: ```R m margins(m, iris, at = list(Species = c("setosa", "versicolor"))) Average marginal effects at specified values lm(formula =...

Hi @langbe it's not going to be part of marigns, unfortunately, as I want the concepts to be in different packages for clarity. But you're right that this is what...

Thanks. Seems like a bug.

This is by design. `margins()` reports effects at the scale of the original variable, not the term generated by `I()`.