Fix domain specification docstrings of ordered distributions

[ricardoV94]

Comment from #7457 (comment)

This shouldn't be in discrete.rst but in the docs of the OrderedLogistic/Probit functions.

Also as @AllenDowney mentioned the description of the distributions are themselves wrong:

pymc/pymc/distributions/discrete.py

Line 1192 in d313012

from 1 to K as a function of some predictor, :math:`\eta`. The

[rahul3002]

I would like to work on this issue its pretty straight forward

[Sourabh-Kumar7]

Hi, I would like to work on this

[ricardoV94]

Anybody can work on it, just open a PR and link to it (after checking there's not already a PR)

[Pratz2005]

Hi @ricardoV94 can you help me understand the issue,

is it that the note ' The OrderedLogistic and OrderedProbit distributions expect the observed values to be 0-based, i.e., they should range from 0 to K-1. Using 1-based indexing (like 1, 2, 3,...K) can result in errors' should not be in discrete.rst but in logs of OrderedLogistic and OrderedProbit instead of it being from (1 to K) right(which is what the current logs is)?

[AtulBoyal]

Hi, I’d love to work on this issue as my first contribution. Is it still available? If so, I’d like to start working on it!