CompatHelper: bump compat for StatsModels to 0.7, (keep existing compat)

[github-actions[bot]]

This pull request changes the compat entry for the StatsModels package from 0.6 to 0.6, 0.7. This keeps the compat entries for earlier versions.

Note: I have not tested your package with this new compat entry. It is your responsibility to make sure that your package tests pass before you merge this pull request.

[codecov[bot]]

Codecov Report

Patch and project coverage have no change.

Comparison is base (b4afc92) 76.86% compared to head (0752aa4) 76.86%.

Additional details and impacted files

```diff @@ Coverage Diff @@ ## master #484 +/- ## ======================================= Coverage 76.86% 76.86% ======================================= Files 25 25 Lines 1664 1664 ======================================= Hits 1279 1279 Misses 385 385 ``` Help us with your feedback. Take ten seconds to tell us [how you rate us](https://about.codecov.io/nps?utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=JuliaInterop). Have a feature suggestion? [Share it here.](https://app.codecov.io/gh/feedback/?utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=JuliaInterop)

:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Do you have feedback about the report comment? Let us know in this issue.

[kleinschmidt]

CI failures seem unrelated (all on ubuntu, failing on a test case that's unrelated AFAICT).

however, sending FunctionTerms to R via exorig is maybe not the best idea since this may not be accurate for FunctionTerms that are constructed outside a @formula (which is now actually possible whereas it was not in 0.6). I don't know what the alternative would be though....one possibility is crawling the function argument tree and building up a Sexp (although it's possible that you'd hit a non-vanilla term in that tree somewhere taht would not have any reasonable Sexp constructor provided...but maybe that's better than hoping that the surface syntax that generated it works the same way in R, I dunno...)

[palday]

This passes locally on my Ubuntu-derivative machine, might be worthwhile to just restart CI. It would be nice to have this compat bump released.

[palday]

@kleinschmidt I fixed CI in #486 -- do you want to give a 👍 as StatsModels rep?