Thomas J. Leeper

Need to match output of margins: ```R > summary(margins::margins(mod)) factor AME SE z p lower upper group2 8.9454 0.9710 9.2129 0.0000 7.0423 10.8485 group3 18.5723 1.5032 12.3552 0.0000 15.6261 21.5185...

This is now working for `lm()`: ```R > summary(prediction(lm(mpg ~ cyl*am, mtcars), at = list(cyl = 4:8, am = 0:1))) at(cyl) at(am) Prediction SE z p lower upper 4 0...

Stata Benchmarks: ```Stata . webuse margex (Artificial data for margins) . logit outcome i.sex i.group Iteration 0: log likelihood = -1366.0718 Iteration 1: log likelihood = -1207.4432 Iteration 2: log...

Reference for all GLMs: http://indiana.edu/~jslsoc/stata/ci_computations/spost_deltaci.pdf

Further Stata benchmarks: ```Stata . quietly logit outcome distance . margins Predictive margins Number of obs = 3,000 Model VCE : OIM Expression : Pr(outcome), predict() ------------------------------------------------------------------------------ | Delta-method |...

Thanks - I'll investigate.

Hmm. Unfortunately, I'm not able to reproduce this error.

Thanks. I'll investigate.

`prediction()` doesn't per se do anything. The `na.action` is actually handled by `find_data()` (in the default case) here: https://github.com/leeper/prediction/blob/master/R/find_data.R#L48-L51 I really haven't tested that much. On the second point, I...

Thanks or this and sorry for long delay in reviewing. Looks good to me. Can you rebase and resubmit (there are some merge conflicts)? If not, I'll try to get...