Using predictions from arbitrary models to get tighter confidence intervals

[luu]

https://statmodeling.stat.columbia.edu/2023/05/04/using-predictions-from-arbitrary-models-to-get-tighter-confidence-intervals/

[tbalsam]

Don't forget that this is eventually inherently limited by the Cramér–Rao bound!

Wiki link: https://en.m.wikipedia.org/wiki/Cram%C3%A9r%E2%80%93Rao_boun...

[clircle → tbalsam]

Only for unbiased estimates

[spekcular → clircle]

There's also a C-R bound for the biased case.