Ari Hartikainen

#### Describe the bug Currently defined formula is right only on even number of samples. num_samples_saved = (self.num_samples + self.num_warmup * self.save_warmup) // self.num_thin In `stan` C++ the samples are...

This PR changes the backend to CmdStanPy.

Init should have `from .pybrms import *`

Support cmdstanpy

1

I think using CmdStanPy should be supported (and be default).

Plotting with ArviZ

2

Hi, package looks great. Due to the use of PyStan (maybe in future of CmdStanPy too) this package is already supported by ArviZ, but I think we should add some...

Update mcse_sd calculation to not use normality assumption.

1

Fixes #2005 See https://github.com/stan-dev/posterior/pull/233/files ## Description ## Checklist - [ ] Follows [official](https://github.com/arviz-devs/arviz/blob/main/CONTRIBUTING.md#pull-request-checklist) PR format - [ ] Includes a sample plot to visually illustrate the changes (only for plot-related...

And other data that can be transformed to InferenceData and then to dataframe to support wide -format tables,

#### Describe the bug Stan 2.33 brings us Tuple datatype. I think we need to handle this with a custom numpy dtype depending on the tuple type. How can we...

#### Describe the bug Stan 2.33.0 drops support for the older way of using arrays and the new array syntax is needed.

With the latest release, the Pathfinder algorithmnwas added to the Stan library. We should investigate how we can use this.