Proper Scoring Rules for Discretized Log-Normal Forecasts

Compute scores for discretized log-normal forecasts. The function is vectorized and preserves the dimension of the input.

scores_lnorm_discrete(x, meanlog, sdlog, which = c("dss", "logs"))

Arguments

x

the observed counts.

meanlog, sdlog

parameters of the log-normal distribution, i.e., mean and standard deviation of the distribution on the log scale.

which

a character vector specifying which scoring rules to apply. The Dawid-Sebastiani score ("dss") and the logarithmic score ("logs") are available and both computed by default.

Value

scores for the predictions of the observations in x (maintaining their dimensions).