Timeline for Example of a (strictly) proper scoring rule on a general measurable space?
Current License: CC BY-SA 4.0
4 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Oct 18, 2020 at 3:37 | comment | added | usul | Never mind - see my other answer; G&R give an example of the continuous ranked probability score (CRPS). | |
| Oct 17, 2020 at 10:46 | comment | added | usul | @aduh, yeah, it's a great question. I can give the above nontrivial weakly proper rules, but I wonder if there might not exist a strictly proper one. | |
| Oct 17, 2020 at 2:55 | comment | added | aduh | Thanks for this. You're right that restricting $\mathcal P$ can be important. I suppose I should clarify, then, that my question is about the case where $\mathcal P$ is the set of all probability measures on some space. To make this more concrete, let $(\Omega, \mathcal A)$ be the unit interval with its Borel algebra. What's an explicit example of a strictly proper scoring rule on the set $\mathcal P$ of all probability measures on $(\Omega, \mathcal A)$? | |
| Oct 15, 2020 at 6:29 | history | answered | usul | CC BY-SA 4.0 |