Proper scoring rule: Difference between revisions

Proper scoring rule (edit)

26 bytes removed , 9 months ago

no edit summary

177

edits

Revision as of 03:21, 10 April 2022 (edit) Vluzko (talk \| contribs) (Expansion of the formal definition.) Tag: Visual edit: Switched ← Older edit		Latest revision as of 09:06, 6 October 2023 (edit) (undo) Nikos (talk \| contribs) No edit summary
(5 intermediate revisions by 3 users not shown)
Line 1: A proper scoring rule is ~~proper~~a ifsubset ~~the~~of ~~expected~~scoring ~~score~~rules iswhich ~~maximized when~~incentivize the forecaster ~~reports~~to report their true subjective probability distribution. {{Wikipedia\|Scoring_rule#StrictlyProperScoringRules}} * Besiroglu, Tamay. ''[https://www.metaculus.com/questions/1505/why-it-is-rational-to-predict-according-to-your-true-beliefs/ Why it is rational to predict according to your true beliefs]'' For the binary case, suppose a forecaster believes the outcome will occur with probability <math>p</math> and reports belief <math>b</math>, which will be scored by the rule <math>f</math>. <math>f</math> is proper if <math>E[f(b, x)]</math> is maximized when <math>b = p</math> [[Category:Proper scoring rules]]