Rationale for df in glance


I was wondering about the rationale for the df values outputted by the glance() function for outputting an lm object. I understand that what is being outputted are the number of model coefficients being estimated (call this k), but why not k-1 since glance() is also outputting information relevant to the F-test?


There's an open issue/discussion in the broom repo related to this you might take a look at:

Thanks Mara and RStudio

Even after googling I did not find this issue. Either my brain, or googling ability has diminished. Sounds like it will be addressed in the next broom update and is already addressed in the dev version.

Thanks again!

This topic was automatically closed 21 days after the last reply. New replies are no longer allowed.