Comparing Probabilistic Forecasting Systems with the Brier Score

By C. Ferro. 2007

99 citations recorded by the source corpus.

Subfields: Atmospheric Science, Global and Planetary Change, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/da535df443b66cbdb16d074fdcc4e05b4f507aeb

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atmospheric Science

In Global and Planetary Change

In Management Science and Operations Research

Citations in the corpus

A bias‐corrected decomposition of the Brier score (2012, methodology): “For individual data sets, standard errors and confidence intervals for the three components might be estimated using ideas similar to those employed by Ferro (2007).”
Sampling Uncertainty and Confidence Intervals for the Brier Score and Brier Skill Score (2008, methodology): “For probability forecasts, sampling theory has been applied to evaluate the sampling uncertainty of the bias (Schwartz 1992; Carpenter and Georgakakos 2001) and accuracy measures (Ferro 2007).”
Two Extra Components in the Brier Score Decomposition (2008, background): “Third, it can allow cleaner comparison of Brier score components for forecasting systems having different numbers of ensemble forecasts (Mullen and Buizza 2002; Ferro 2007).”
Initial perturbations based on the ensemble transform (ET) technique in the NCEP global operational forecast system (2008, methodology): “The impact on Brier score by changing ensemble size was studied recently by Ferro (2007). Shown in Fig.”
Probabilistic Seasonal Forecasts in the North American Multimodel Ensemble: A Baseline Skill Assessment (2016, background): “The standard error in a Brier score is inversely proportional to the squared sample size (Ferro 2007).”
Assessment of representations of model uncertainty in monthly and seasonal forecast ensembles (2011, methodology): “for hypothetical infinite ensemble sizes [Ferro, 2007] has been used to minimise the effect on the skill measure of sampling uncertainty due to the different ensemble sizes of the three systems.”
The Matthews Correlation Coefficient (MCC) is More Informative Than Cohen’s Kappa and Brier Score in Binary Classification Assessment (2021, methodology): “Roulston [81], Stephenson and colleagues [82], and Ferro et al. [83] investigated some mathematical properties of the Brier score.”
Sampling distributions of the Brier score and Brier skill score under serial dependence (2010, background): “The results presented here have considered only singlelocation forecast series, and have assumed a (latent) first-order autoregressive time correlation structure that is stationary across the entire verification sample. Nonhomogeneous verification samples should of course be stratified before applic”