File Exchange

image thumbnail

Continuous rank probability score

version 1.0.0.0 (6.73 KB) by Durga Lal Shrestha
Calculates continuous rank probability score (CRPS) for probabilistic and ensemble forecasts

8 Downloads

Updated 11 Sep 2014

View License

The CRPS measures the closeness of forecast distribution (fcst) and corresponding observation (obs). This score is widely used in forecast verification.

[mean_CRPS] = crps(fcst,obs);
[mean_CRPS] = crps(fcst,obs,plot_pos);
[mean_CRPS,crps_values,num] = crps(fcst,obs);

INPUT
obs: Vector of observations
fcst: Matrix of Ensemble forecast of size N x M. NB: N must equal length(obs), M equals the number of ensemble members
plot_pos: plotting positions that determine cumulative distribution function

OUTPUT
mean_CRPS: Mean of non missing CRPS values
crps_values: A vector (length n) of CRPS values
num: number of non missing CRPS values used to compute mean_CRPS

EXAMPLES:
fcst = rand(1000,1000);
obs = rand(1000,1);
[meanCRPS] = crps(fcst,obs);

Cite As

Durga Lal Shrestha (2020). Continuous rank probability score (https://www.mathworks.com/matlabcentral/fileexchange/47807-continuous-rank-probability-score), MATLAB Central File Exchange. Retrieved .

Comments and Ratings (1)

Hello! I would like to know for what reason are negatives values treated as missing values?

MATLAB Release Compatibility
Created with R2014a
Compatible with any release
Platform Compatibility
Windows macOS Linux