Fix formatting in documentation of AR distribution parameters

[daniel-saunders-phil]

What is this PR about?

Fixed a variety of docstring issues for the pm.AR distribution.

...

Checklist

• Explain important implementation details 👆
• Make sure that the pre-commit linting/style checks pass.
• Link relevant issues (preferably in nice commit messages)
• Are the changes covered by tests and docstrings?
• Fill out the short summary sections 👇

Major / Breaking Changes

• ...

Bugfixes / New features

• ...

Docs / Maintenance

• Fix formatting in documentation of AR distribution parameters

[codecov]

Codecov Report

Merging #6080 (0683b0a) into main (c8ce9c9) will increase coverage by 4.01%.
The diff coverage is n/a.

@@            Coverage Diff             @@
##             main    #6080      +/-   ##
==========================================
+ Coverage   85.52%   89.53%   +4.01%     
==========================================
  Files          72       72              
  Lines       12933    12933              
==========================================
+ Hits        11061    11580     +519     
+ Misses       1872     1353     -519     

Impacted Files	Coverage Δ
pymc/distributions/timeseries.py	77.99% <ø> (+34.62%)	⬆️
pymc/distributions/continuous.py	97.51% <0.00%> (+0.10%)	⬆️
pymc/sampling.py	82.15% <0.00%> (+0.11%)	⬆️
pymc/printing.py	86.66% <0.00%> (+0.95%)	⬆️
pymc/distributions/multivariate.py	92.03% <0.00%> (+0.98%)	⬆️
pymc/distributions/discrete.py	99.21% <0.00%> (+1.56%)	⬆️
pymc/util.py	77.64% <0.00%> (+2.35%)	⬆️
pymc/backends/arviz.py	90.61% <0.00%> (+4.48%)	⬆️
pymc/step_methods/hmc/quadpotential.py	80.69% <0.00%> (+6.93%)	⬆️
pymc/data.py	80.08% <0.00%> (+12.19%)	⬆️
... and 4 more

[reshamas]

#DataUmbrellaPyMCSprint

[cluhmann]

This looks good to me. The only question I would have is about the "unnamed distribution" which seems correct, but there may be some other "docstring-official" way of specifying this. Not sure.

[cluhmann]

And thank you for your contribution @daniel-saunders-phil !

[ricardoV94]

This looks good to me. The only question I would have is about the "unnamed distribution" which seems correct, but there may be some other "docstring-official" way of specifying this. Not sure.

We should make one like tensor_like, but there isn't any right now. Do you want to open an issue to track that?

[OriolAbril]

"unnamed distribution" should be Distribution which for now points to the API section with all distributions, we could update it at any point to be a glossary term. The fact it is unnamed is not related to the type but to a property some objects with this type have and that info should be described at the parameter description section (which is already done, so no changes needed here).

[cluhmann]

Yeah, I think a glossary term would be good, because I suspect that stating that this argument should be a "Distribution" is going to cause some confusion. Chime in here.