Evaluation of probabilistic prediction systems for a scalar variable

By G. Candille, O. Talagrand. 2005

261 citations recorded by the source corpus.

Subfields: Atmospheric Science, Environmental Engineering, Global and Planetary Change

View Paper: https://www.semanticscholar.org/paper/c3b6e479ec81d1ead78f7522aabfdd8e5d0aa306

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 Environmental Engineering

In Global and Planetary Change

Citations in the corpus

The discrete brier and ranked probability skill scores (2007, background): “In particular, a predicted probability cannot be verified by a single observation (Candille and Talagrand 2005).”
The continuous ranked probability score for circular variables and its application to mesoscale forecast ensemble verification (2006, background): “Additionally, Hersbach (2000) and Candille and Talagrand (2005) describe reliability-resolution (or calibration-sharpness) decompositions of the linear CRPS. The linear CRPS and the negative of the logarithmic score (information deficit or ignorance score) are seeing increased use in probabilistic w”
Comparison between Singular Vectors and Breeding Vectors as Initial Perturbations for the ECMWF Ensemble Prediction System (2008, methodology): “To measure the probabilistic skill of the ensemble systems we have used the RPSS (Candille and Talagrand 2005), the ROC area (Wilks 2006), and the ISS (Roulston and Smith 2002).”
Ensemble forecasting (2008, background): “[18] for a more comprehensive overview and further references.”
Probabilistic forecasts, calibration and sharpness (2007, methodology): “Candille and Talagrand (2005) discussed calibration–sharpness decompositions of the continuous ranked probability score.”
Calibrated Surface Temperature Forecasts from the Canadian Ensemble Prediction System Using Bayesian Model Averaging (2007, methodology): “Candille and Talagrand (2005) point out that, due to the finite sample size, the expected value of the sum is [MN/(N 1)].”
Assessing probabilistic forecasts of multivariate quantities, with an application to ensemble predictions of surface winds (2008, methodology): “This scoring rule can be traced back to Matheson and Winkler (1976) and is increasingly being used in the meteorological community (p. 252, Hersbach 2000; Candille and Talagrand 2005; Wilks 2006).”
Strictly Proper Scoring Rules, Prediction, and Estimation (2007, background): “The CRPS lately has attracted renewed interest in the atmospheric sciences community (Hersbach 2000; Candille and Talagrand 2005; Gneiting, Raftery, Westveld, and Goldman 2005; Grimit, Gneiting, Berrocal, and Johnson 2006; Wilks 2006, pp. 302–303).”
Impact of observational error on the validation of ensemble prediction systems (2008, unknown): “Because of severe limitations in practical computations (Candille and Talagrand, 2005), results about CRPS are not included in this paper.”
Forecast verification: current status and future directions (2008, background): “Candille and Talagrand (2005) proposed an useful formula which allows quantitative assessment of the ‘departure from flatness’ of a rank histogram (see also Smith, 2001).”
Two Extra Components in the Brier Score Decomposition (2008, background): “2 of Atger (2004) and is to be expected from general mathematical considerations (Candille and Talagrand 2005).”
A bias‐corrected decomposition of the Brier score (2012, background): “Other decompositions based on the full distributions are preferable (Murphy, 1972; Candille and Talagrand, 2005).”
The Multiensemble Approach: The NAEFS Example (2009, methodology): “The global skill of an EPS is measured by the CRPS (Stanski et al. 1989; Candille and Talagrand 2005).”
Generalization of the Ignorance Score: Continuous Ranked Version and Its Decomposition (2012, background): “Candille and Talagrand (2005) also presented the decomposition in (8); however, they stated that a practical calculation requires ‘‘many approximations and assumptions,’’ assuming a prior transformation of each predicted ensemble into a continuous distribution function is necessary.”
Performance and reliability of multimodel hydrological ensemble simulations based on seventeen lumped models and a thousand catchments (2010, unknown): “The selected score is the Continuous Ranked Probability Score (CRPS) (Matheson and Winkler, 1976), which is a proper score widely used in atmospheric and hydrologic sciences (e.g., Gneiting et al., 2005; Candille and Talagrand, 2005; Weber et al., 2006; Boucher et al., 2009).”