Josh Speagle

> I don't know if @joshspeagle has an opinion on this, but I don't really see the point of n_effective for static/initial sampling (unless I miss something). I don't either,...

> My only thought now, is whether it's better for the user to still allow staticnested.run_nested(n_effective=XXX), but instead of deprecation warning throw a RuntimeWarning saying that it's a no-op. Thiis...

Adding in warnings for this particular edge case (literally, hah) does sound like a good idea.

Awesome! I'm out on vacation for a few days, but will try to merge this in over the next week.

Yes, I definitely plan to run a battery of additional tests on harder functions to just check this behaves well. :) Assuming everything goes well, I'll plan to merge it...

So I've now made enough code changes trying to resolve other issues (due to my delay in merging this) that I might have to incorporate some of these changes by...

These are an instructive set of plots and a useful set of tests. Quick comments (in order of points): - The oscillations in the number of ellipsoids and the corresponding...

> I'd say we need a function belonging to Results or to Sampler. Something like validate() with a few options. Would you envision something like that being run at various...

The results from 1 and 2 here are why they ended up being disabled by default, since they require a huge number of live points to avoid becoming overly enlarged...

Just a note to myself that it might be cool to try and add in some of these utilities as part of the code for users to check as part...