Paul-Christian Bürkner

I think we could also use the `mcmc_` prefix for the ESS plots, something like: ``` mcmc_ess_local mcmc_ess_quantile mcmc_ess_change ``` The rank plots could simply be named `mcmc_rank` or similar.

I have thought about this, but not sure if may ideas made sense. Bascially, one reason to have the `draws_list` class (i.e., a list of lists with one element per...

One way of differentiating between tidybayes and posterior functions could be whether data or ploting is involved in addition to posterior draws. So whatever only handles draws could (potentially) go...

@mjskay this is a good point and likely better way to differentiate the packages. I am happy to be involved in a chat if needed.

Is there anything to be done for this issue still? I think time has basically told quite well what should be in posterior and what should be in tidybayes. @mjskay...

Thanks! I will think a little more about it and then revisit this issue. In the meantime, what do others think?

Thank you both for discussing this issue. I have no good opinion on whether we shall support weights in `rvar`s. I leave this @mjskay's discretion on whether he things that...

That could be an option, yes. Not sure yet though if it would be a good idea to add `...` to all of our rhat and ess functions. We can...

There is no support for HDIs yet but it might be a reasonable addition. The problem is the HDI rely on density estimates which require many more draws in order...

Thinking more about the generics above, I think there is one conceptual issue, which we need to resolve related to #8 and #13. `posterior_predict` and related methods usually return a...