Seth Axen

As if right now, yes, but it's unclear when I will finish it. I have a private lightweight repo efficiently implementing various intrinsic circular statistics that I will eventually finish,...

Also, when the evaluation points are different from the sample points, it feels a little weird using step plots. Step plots give the sense that we know what the function...

@OriolAbril when you get a chance, can you take a look at this?

@OriolAbril I've implemented all suggestions and updated the above description and changelog. This should be ready for final review.

> After seeing the warnings and trying it out I am a bit on the fence on the behaviour of `eval_points`. It is basically a required argument right now, otherwise...

IIRC, we merged this quickly from the GSOC work but didn't advertise it so that we could improve it before doing so. It also uses random sampling for the bands,...

> do you remember the main issues @sethaxen ? If so, could you open an issue? No, I don't, I'm sorry. And looking back through Slack and GitHub, I'm not...

I originally didn't implement `JointOrderStatistics` for discrete distributions because its pmf looked really complicated (from https://doi.org/10.1137/1.9780898719062.ch3):  But on a closer look, $r_s - r_{s-1}$ is just the count of...

`Censored` is an example of a probability measure of mixed type (see e.g. https://www.randomservices.org/random/dist/Mixed.html). While a density function is generally a Radon-Nikodym derivative of a probability measure wrt another measure...

I have some local implementations I'll polish for a PR. I also looked at the same for MatrixBeta, but there's no way to use the factorization for its logpdf, just...