scoringutils (version 0.1.4)

logs: LogS

Description

Wrapper around the logs_sample function from the scoringRules package. Used to score continuous predictions. While the Log Score is in theory also applicable to integer forecasts, the problem lies in the implementation: The Log Score needs a kernel density estimation, which is not well defined with integer-valued Monte Carlo Samples. The Log Score can be used for specific integer valued probabiliy distributions. See the scoringRules package for more details.

Usage

logs(true_values, predictions)

Arguments

true_values

A vector with the true observed values of size n

predictions

nxN matrix of predictive samples, n (number of rows) being the number of data points and N (number of columns) the number of Monte Carlo samples

Value

vector with the scoring values

References

Alexander Jordan, Fabian Kr<U+00FC>ger, Sebastian Lerch, Evaluating Probabilistic Forecasts withscoringRules, https://arxiv.org/pdf/1709.04743.pdf

Examples

# NOT RUN {
true_values <- rpois(30, lambda = 1:30)
predictions <- replicate(200, rpois(n = 30, lambda = 1:30))
logs(true_values, predictions)
# }