Carlos Parada

Typically, Bayesian models.

Having a similar problem, but adding the token doesn't seem to fix it? Might be that the instructions are unclear -- for instance, I don't know if I should encase...

Unfortunately I don't have something small, since I pulled the .dta file that had this problem off the internet :sweat_smile: But the file I tried to load is [here](https://www.journals.uchicago.edu/doi/suppl/10.1086/708815). The...

If I can make a suggestion, it would be nice if: 1. Any features in this package missing from base were added there--which I believe is just `Align`--and 2. This...

> Thanks for the suggestion! I'm not sure about 1, I think that would be up to base. I haven't checked whether `Slices` in base does more or less things...

@bramtayl I've checked, and the only differences are: 1. The `Slices` in Base don't implement `Align`. 2. The `Slices` in Base are constructed using `eachslice`, and don't have a constructor...

> The eager `Align` is `stack`, and my understanding is that people were not so keen on adding a lazy version. While a view from `eachcol` is almost always as...

Looks like there's not much interest in a PR to base; in that case, I think the package should be able to just implement a `Slices` constructor following the old...

The problem is that the Turing model has an error; it is using `MvNormal` to mean a sequence of independent, normally-distributed values. However, `MvNormal` is supposed to be used when...

(Don't worry, this is a very common mistake -- common enough that I should probably add an explanation when the model has a sample size of 1 :smile:)