climFairRpss: Calculate Fair Ranked Probability Skill Score Against...

In jonasbhend/easyVerification: Ensemble Forecast Verification for Large Data Sets

Calculate Fair Ranked Probability Skill Score Against Climatological Reference Forecast.

Description

Calculate the fair ranked probability skill score (fair RPSS) between an ensemble forecasts and a climatological reference forecast derived from the observations. The categories of the climatological reference forecast have been defined based on the distribution of the observations and the exact forecast probabilities are known. The 'fair' correction therefore should not be applied to the reference forecast.

Usage

climFairRpss(ens, ens.ref, obs, format = c("category", "member"))

Arguments

ens	N*K matrix. ens[i,j] is the number of ensemble members that predict category j at time i.
ens.ref	N*K matrix, similar to ens
obs	N*K matrix. obs[i,j] = 1 if category j is observed at time i, 0 otherwise.
format	additional argument for use with SpecsVerification >= 0.5. Do not change this argument manually (except when using climFairRpss, as standalone function).

Value

A list with the following elements: rpss|skillscore: The value of the skill score. sigma.rpss|skillscore.sd: The standard deviation of the skill score, approximated by propagation of uncertainty. Please note that the naming changes with the new version of SpecsVerification.

See Also

veriApply

Examples

tm <- toymodel()

## compute RPSS using veriApply
veriApply("climFairRpss", tm$fcst, tm$obs, prob = 1:2 / 3)

jonasbhend/easyVerification documentation built on Aug. 21, 2023, 2:31 p.m.