Log score: Difference between revisions
Improved introduction
No edit summary |
(Improved introduction) |
||
Line 3:
The Log score<ref>[https://www.jstor.org/stable/2984087 Rational Decisions] -
I. J. Good, 1954</ref> (
All [[Metaculus]] scores are types of log score<ref>https://www.metaculus.com/help/faq/#log_score</ref>.
== Definition ==▼
It was first proposed by [https://en.wikipedia.org/wiki/I._J._Good I. J. Good] in 1952 to evaluate binary forecasts. The score is commonly to score predictions and evaluate how good a distribution captures the observed data, for example in Bayesian statistics. For non-binary questions and up to affine transformations, the log score is the only<ref>[https://en.wikipedia.org/wiki/Scoring_rule#Locality]</ref> strictly proper local scoring rule, meaning that the score depends only on the probability (or [https://en.wikipedia.org/wiki/Probability_density_function probability density]) assigned to the actually observed outcome, rather than on the entire predictive distribution.
▲== Definition ==
The log score is usually computed as the negative logarithm of the predictive density evaluated at the observed value <math>y</math>, i.e. <math>\text{log score}(y) = -\log f(y)</math>, where <math>f()</math> is the predictive probability density function. Usually the natural logarithm is used, but the log score remains strictly proper for any base <math>> 1</math> used for the logarithm.
In the formulation presented above, the score is negatively oriented, meaning that smaller values are better. Sometimes the sign of the log score is inversed and it is simply given as the log predictive density. If this is the case, then larger values are better.
|