brier_score: Brier Score

In nikosbosse/scoringutils2:

Description

Computes the Brier Score for probabilistic forecasts of binary outcomes.

Usage

brier_score(true_values, predictions)

Arguments

true_values	A vector with the true observed values of size n
predictions	A vector with a predicted probability that true_value = 1.

Details

The Brier score is a proper score rule that assesses the accuracy of probabilistic binary predictions. The outcomes can be either 0 or 1, the predictions must be a probability that the true outcome will be 1.

The Brier Score is then computed as the mean squared error between the probabilistic prediction and the true outcome.

Brier_Score = \frac{1}{N} ∑_{t = 1}^{n} (prediction_t - outcome_t)^2

Value

A numeric value with the Brier Score, i.e. the mean squared error of the given probability forecasts

Examples

true_values <- sample(c(0,1), size = 30, replace = TRUE)
predictions <- runif(n = 30, min = 0, max = 1)

brier_score(true_values, predictions)

nikosbosse/scoringutils2 documentation built on Jan. 8, 2021, 12:12 p.m.