Carlos Parada

> I thought AxisKeys or NamedDims are the most common replacements for and improvements over AxisArrays these days but I didn't keep track of recent developments. There are many different...

Implemented LOO-CV [here](https://github.com/ParadaCarleton/ParetoSmooth.jl). Feel free to import and reexport it.

> `aic` etc. are defined in StatsBase: https://github.com/JuliaStats/StatsBase.jl/blob/2faa6e80b7966b915086d8cd5a4a4d89a2126db5/src/statmodels.jl#L192 I think `dic` etc. should be defined in a similar way if possible: there's some lightweight functional interface (such as `loglikelihood`) and...

> Thanks for all your input. I'll be holding off on PSIS-LOO then, hearing that there is already ongoing work on it. First focus is to explore good/simple ways to...

> I think it would be great if there would be support for Makie for `Chains`. However, as long as there is no lightweight recipe support for Makie, similar to...

> Another idea is to have something like a Tables interface for collections of MCMC draws produced in a Bayesian workflow. This would give a unified interface for retrieving prior,...

> I guess some things to consider are: > > * what are the pros and cons of `DimArray`s compared with `AxisArray`s? > * how breaking is it, for developers...

Mentioning @cpfiffer who I think has mentioned not liking AxisArrays. I could get a PR up in a couple days if you'd like.

Yep, sorry, I meant to put it in there 😅

> Ideally we would allow to use matrices/3d arrays (current setup) as well as StructArrays (as discussed in some of the issues or PRs IIRC). Both have their advantages and...