Of Quantiles and Expectiles: Consistent Scoring Functions, Choquet Representations and Forecast Rankings

DOI10.1111/rssb.12154zbMath1414.62038arXiv1503.08195MaRDI QIDQ5378146

Alexander I. Jordan, Fabian Krüger, Tilmann Gneiting, Werner Ehm

Publication date: 12 June 2019

Published in: Journal of the Royal Statistical Society Series B: Statistical Methodology (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1503.08195

zbMATH Keywords

decision theory; quantile; expectile; probability forecast; forecast ranking; economic utility; Choquet representation; point forecast; consistent scoring function; elicitable; order sensitivity

Mathematics Subject Classification ID

62M20: Inference from stochastic processes and prediction

62G05: Nonparametric estimation

62F10: Point estimation

91B06: Decision theory

62-02: Research exposition (monographs, survey articles) pertaining to statistics

62F07: Statistical ranking and selection procedures

62C05: General considerations in statistical decision theory

Related Items

Quantile Evaluation, Sensitivity to Bracketing, and Sharing Business Payoffs, Simultaneous Semiparametric Estimation of Clustering and Regression, Calibrating sufficiently, An elastic-net penalized expectile regression with applications, Scalable spatio‐temporal Bayesian analysis of high‐dimensional electroencephalography data, Comparative evaluation of point process forecasts, Regression diagnostics meets forecast evaluation: conditional calibration, reliability diagrams, and coefficient of determination, Sensitivity measures based on scoring functions, Using proxies to improve forecast evaluation, A joint quantile and expected shortfall regression framework, On the nonparametric estimation of the functional expectile regression, Forecast dominance testing via sign randomization, Forecaster's dilemma: extreme events and forecast evaluation, Elicitability and identifiability of set-valued measures of systemic risk, Scoring interval forecasts: equal-tailed, shortest, and modal interval, Forecast evaluation of quantiles, prediction intervals, and other set-valued functionals, The \(k\)th power expectile regression, On the elicitability of range value at risk, The functional \(k\mathrm{NN}\) estimator of the conditional expectile: uniform consistency in number of neighbors, Receiver operating characteristic (ROC) movies, universal ROC (UROC) curves, and coefficient of predictive ability (CPA), Characterizing the optimal solutions to the isotonic regression problem for identifiable functionals, Point forecasting and forecast evaluation with generalized Huber loss, Joint inference on extreme expectiles for multivariate heavy-tailed distributions, Isotonic regression for elicitable functionals and their Bayes risk, Encoded value-at-risk: a machine learning approach for portfolio risk measurement, On automatic bias reduction for extreme expectile estimation, A hierarchical Bayesian model for predicting ecological interactions using scaled evolutionary relationships, Properization: constructing proper scoring rules via Bayes acts, ExpectHill estimation, extreme risk and heavy tails, A discrete density approach to Bayesian quantile and expectile regression with discrete responses, Estimating value-at-risk and expected shortfall using the intraday low and range data, Tail expectile process and risk assessment, Backtesting VaR and expectiles with realized scores, The consistency and asymptotic normality of the kernel type expectile regression estimator for functional data