Reliability of Subjective Probability Forecasts of Precipitation and Temperature

By A. H. Murphy, Robert L. Winkler. 1977

How researchers see this paper

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

Citations in the corpus

Verified Uncertainty Calibration (2019, methodology): “Calibration, including the squared calibration error, has been studied in many fields besides machine learning including meteorology [2, 3, 4, 5, 6], fairness [29, 30], healthcare [1, 31, 32, 33], reinforcement learning [34], natural language processing [7, 8], speech recognition [35], econometrics ”
The ‘heuristics and biases’ bias in expert elicitation (2007, background): “…research has shown that weather forecasters are very accurate: observed relative frequencies correspond very closely to the forecast probabilities, with only a slight tendency to overforecast (for the forecast probabilities to exceed the relative frequencies) (Murphy and Winkler, 1977).”
Skilful precipitation nowcasting using deep generative models of radar (2021, methodology): “Reliability and Sharpness Diagrams We use reliability diagrams [42] to measure calibration for ensemble forecasts of whether rain exceeds a threshold t .”
The Implicit Fairness Criterion of Unconstrained Learning (2018, background): “The concept of calibration has a venerable history in statistics and machine learning (Cox, 1958; Murphy and Winkler, 1977; Dawid, 1982; DeGroot and Fienberg, 1983; Platt, 1999; Zadrozny and Elkan, 2001; Niculescu-Mizil and Caruana, 2005).”
Local Temperature Scaling for Probability Calibration (2020, methodology): “As it is difficult to work directly with this definition to assess miscalibration, we extend several visual and quantitative metrics [11, 53, 54, 56, 57], which have previously been proposed in the context of classification.”
Evaluating model calibration in classification (2019, methodology): “…reliability diagrams A classical reliability diagram is a method to investigate the miscalibration of a binary probabilistic classifier (see Murphy and Winkler 1977; Bröcker 2008, for an early and a more recent account) by plotting for one class the average prediction versus the regression…”