ss: Skill Score

In jobstdavid/eppverification: Verification Tools for the Statistical Postprocessing of Ensemble Forecasts

Skill Score

Description

This function calculates the Skill Score (SS) of the mean score time series.

Usage

ss(s1, s2, na.action = na.omit, aggregate = FALSE, ...)

Arguments

s1	vector of mean scores from method 1
s2	vector of mean scores from method 2
na.action	function to handle the NA's. Default: na.omit.
aggregate	logical or function for aggregating the single scores, e.g. sum, mean, weighted.mean, .... Default: FALSE, i.e. no aggregation function.
...	further arguments passed to the aggregate function.

Details

The Skill Score (SS) uses the mean scores s1 of the forecasting method of interest (method 1) and s2 of the benchmark method (method 2). Consequently, the Skill Score can be calculated via

\text{SS}=1-\frac{s_1}{s_2},

indicating the relative improvement of method 1 over method 2.

Skill scores are positively oriented with a maximum value of 1. Positive values indicate an improvement of method 1 over method 2, negative values stand for a worse performance of method 1 over method 2.

Value

Skill score.

Author(s)

David Jobst

References

Gneiting, T. and Raftery, A. (2007). Strictly proper scoring rules, prediction, and estimation. Journal of the American Statistical Association, 102, 359-378.

Examples

# simulated data
s1 <- rnorm(100)
s2 <- rnorm(100)

ss(s1 = s1, s2 = s2)
ss(s1 = s1, s2 = s2, aggregate = mean)

jobstdavid/eppverification documentation built on May 13, 2024, 5:20 p.m.