Edward A. Roualdes

Thanks, y'all, for getting this going. In the last week, I've missed out on two new features that Eigen 3.4 brings.

I just submit 2 pull requests, one in https://github.com/stan-dev/stan/pull/2501, which matches tests across int_step.stan and step.stan and one in https://github.com/stan-dev/math/pull/805, in which the step function definitions were changed and tests...

Thanks, @avehtari. I think `autocovariance` is in `stan-dev/math`. I'll start this week to work on these.

The reference values from the R implementation was a great idea, thank you. Just one weird issue about it. When I run the following R code, ``` library(rstan) source('monitor.R') upath

Thanks for double checking. Let me know what you guys think of the following functional spec. I propose to overload `stan::analyze::compte_effective_sample_size()` with ``` double compute_effective_sample_size(std::vector draws, std::vector sizes) // and...

> I’m wondering if internally this all can’t be handled with Eigen maps? I thought about and tried this, but I convinced myself that it won't work. An Eigen map...

> I wasn’t thinking of merging everything into a matrix via a map but rather handling the initial chains, or any splitting there of, as a collection of vector maps....

> splitting the chains can be accomplished by creating a new collection of std::vectors that point to segments of the input std::vector memory That's a reasonable way to split chains...

> But this requires two implementations of the analyze function, right? That’s what I want to move away from. Yes. And I agree, this design choice suffers from all the...

Your third idea seems best to me, but possibly because I can't differentiate it from what already exists. This is likely just my misunderstanding. Would you mind giving a short...