Carlos Parada

I think any differences in terms of actual speed/efficiency are probably pretty small -- writing MCMC samples to memory is not going to be the bottleneck for something like HMC...

Does anybody object, or should I make a pull request reordering axes like this? I've written some PSIS code that assumes this ordering for `ess_rhat`, and would like to know...

@sethaxen @devmotion I can create a PR reordering these axes, and implementing a consistent interface that works with arrays following this standard. In cases where the interface isn't consistent, there's...

Sure, we can handle this later if you want. As for the other thing, I'm not suggesting that we replace the existing methods or get rid of them, just that...

(Also, the docstring should probably specify whether `loglike` is the log-likelihood function before or after transforming the variables with the prior to fall on the unit cube.)

> In addition, the code that calls the functions (i.e., the proposal algorithms) is using Vectors, since the pool of live points is a Matrix. We could allow users the...

I think we can merge now and work on optimization later. Honestly, it's just a huge pain trying to optimize for allocations without having Transducers.jl, laziness, or good functional primitives...

Has any kind of `AbstractTimeSeries` interface been implemented? I ask because I'm interested in writing up an [autocovariance estimation interface](https://github.com/JuliaStats/StatsBase.jl/issues/774) for StatsBase. I think it'd be very nice to have...

I'm also interested in knowing if this is planned.

I checked, but I didn't see a SplittablesBase.jl in JuliaFolds2 :sweat_smile: