Neal Fultz

I see, so something like this? https://github.com/nfultz/estimatr/commit/ce192679ea35cccd63a4a7e1f21142a77209a697

I think it's related to the robust std errors, works fine when you turn them off: > lm_robust(Y ~ Z + as.factor(x), data = dat, se='classical')

Using the lm method for augment *almost* works, but fails: augment.lm_robust trying to do it myself and got very stuck, very quickly. > > — > You are receiving this...

Since `augment.lm` isn't exported, I think it would be better to add `augment.lm_robust` in the broom package instead of here: ``` augment.lm_robust

That makes sense. estimatr is a bad case, because the model objects are generally compatible with other methods for `lm` but not always. It doesn't have `lm` in it's list...

@acoppock I would recommend just adding the first stage as a named element on the iv_robust_fit object, and not directing people to specify non-standard options on tidy / not also...

We would most def welcome a PR, although I am not sure if there are plans to cut a new release this school year. @acoppock ?

Shouldn't it just affect the width of the CIs? Not the p?

> It would be nice to have at least `residuals()` and `logLik()` implemented (I think logLik needs residuals), to compute indices like AIC etc. the log-liklihood only needs the RSS...

Necroing this thread, please see also http://discuss.declaredesign.org/t/anova-with-lm-robust-objects/127/2 where I hijacked residuals + deviance generics from lm for someone.