Comment about error structure in the marginal effects document

[Ax3man]

Following earlier discussion here:

Perhaps it would be useful to add a comment about setting re_formula = ~ 0, at the part where you warn that "a population made up of equal proportions of all possible values of B being a meaningful thing to talk about." If it is not, then use re_formula = ~0, which is equivalent to how emmeans calculates this.

What would be even better are some examples of cases where each would be appropriate, but I appreciate that's more tricky and more work.

Thanks for these very useful examples!

[mjskay]

Thanks for raising this - somewhere on my todo list is working through a complete example comparing these (and other) different marginal effects, how to calculate them and what they mean. Probably that will turn into a tidybayes vignette. Optimistically, I may have time to play with this in the latter half of December.

[Ax3man]

That would be awesome!

Thanks again.