Higher order elicitability and Osband's principle
From MaRDI portal
Publication:309736
Abstract: A statistical functional, such as the mean or the median, is called elicitable if there is a scoring function or loss function such that the correct forecast of the functional is the unique minimizer of the expected score. Such scoring functions are called strictly consistent for the functional. The elicitability of a functional opens the possibility to compare competing forecasts and to rank them in terms of their realized scores. In this paper, we explore the notion of elicitability for multi-dimensional functionals and give both necessary and sufficient conditions for strictly consistent scoring functions. We cover the case of functionals with elicitable components, but we also show that one-dimensional functionals that are not elicitable can be a component of a higher order elicitable functional. In the case of the variance this is a known result. However, an important result of this paper is that spectral risk measures with a spectral measure with finite support are jointly elicitable if one adds the `correct' quantiles. A direct consequence of applied interest is that the pair (Value at Risk, Expected Shortfall) is jointly elicitable under mild conditions that are usually fulfilled in risk management applications.
Recommendations
- Making and evaluating point forecasts
- Order-sensitivity and equivariance of scoring functions
- On the indirect elicitability of the mode and modal interval
- The mode functional is not elicitable
- Of quantiles and expectiles: consistent scoring functions, Choquet representations and forecast rankings. With discussion and authors' reply
Cites work
- scientific article; zbMATH DE number 3567134 (Why is no real title available?)
- scientific article; zbMATH DE number 1795125 (Why is no real title available?)
- Asymmetric Least Squares Estimation and Testing
- Coherence and elicitability
- Coherent dispersion criteria for optimal experimental design
- Coherent measures of risk
- Comparative and qualitative robustness for law-invariant risk measures
- DISTRIBUTION‐INVARIANT RISK MEASURES, INFORMATION, AND DYNAMIC CONSISTENCY
- Elicitable distortion risk measures: a concise proof
- Elicitation of Personal Probabilities and Expectations
- External risk measures and Basel accords
- Higher order elicitability and Osband's principle
- Law invariant risk measures have the Fatou property
- Making and evaluating point forecasts
- On elicitable risk measures
- On the Optimality of Conditional Expectation as a Bregman Predictor
- On the measurement of economic tail risk
- Qualitative and infinitesimal robustness of tail-dependent statistical functionals
- Quantile regression.
- Quasi-Hadamard differentiability of general risk functionals and its application
- Risk measures with the CxLS property
- Robust Estimation of a Location Parameter
- Robustness and sensitivity analysis of risk measurement procedures
- Strictly Proper Scoring Rules, Prediction, and Estimation
- The mode functional is not elicitable
- Verification of internal risk measure estimates
Cited in
(85)- On the measurement of economic tail risk
- Multistep quantile forecasts for supply chain and logistics operations: bootstrapping, the GARCH model and quantile regression based approaches
- Bayes risk, elicitability, and the Expected Shortfall
- Conditionally Elicitable Dynamic Risk Measures for Deep Reinforcement Learning
- On the elicitability of range value at risk
- Estimating value-at-risk and expected shortfall using the intraday low and range data
- Scenario-based risk evaluation
- Scoring interval forecasts: equal-tailed, shortest, and modal interval
- Isotonic regression for elicitable functionals and their Bayes risk
- Forecast evaluation of quantiles, prediction intervals, and other set-valued functionals
- Multivariate geometric expectiles
- Performance measurement with expectiles
- Forecast dominance testing via sign randomization
- Joint generalized quantile and conditional tail expectation regression for insurance risk analysis
- Optimal operational service levels in vendor managed inventory contracts -- an exact approach
- Of quantiles and expectiles: consistent scoring functions, Choquet representations and forecast rankings. With discussion and authors' reply
- An energy-based measure for long-run horizon risk quantification
- XVA analysis from the balance sheet
- S&P 500 volatility, volatility regimes, and economic uncertainty
- A semi-parametric conditional autoregressive joint value-at-risk and expected shortfall modeling framework incorporating realized measures
- Dynamic expected shortfall: a spectral decomposition of tail risk across time horizons
- Coherence and elicitability
- scientific article; zbMATH DE number 434675 (Why is no real title available?)
- Risk aversion in regulatory capital principles
- Point forecasting and forecast evaluation with generalized Huber loss
- Simple factor realized stochastic volatility models
- Risks in emerging markets equities: time-varying versus spatial risk analysis
- Distortion riskmetrics on general spaces
- Verification of internal risk measure estimates
- Making and evaluating point forecasts
- On the indirect elicitability of the mode and modal interval
- A joint quantile and expected shortfall regression framework
- Elicitability and identifiability of set-valued measures of systemic risk
- The mode functional is not elicitable
- Higher order elicitability and Osband's principle
- Asymptotic stability of empirical processes and related functionals
- Why scoring functions cannot assess tail properties
- Semi-parametric Bayesian tail risk forecasting incorporating realized measures of volatility
- Backtesting expected shortfall and beyond
- Deep quantile and deep composite triplet regression
- PELVE: probability equivalent level of VaR and ES
- Quantile evaluation, sensitivity to bracketing, and sharing business payoffs
- Bayesian realized-GARCH models for financial tail risk forecasting incorporating the two-sided Weibull distribution
- Robustness in the optimization of risk measures
- Robust and Pareto optimality of insurance contracts
- Multivariate extensions of expectiles risk measures
- Uniform calibration tests for forecasting systems with small lead time
- A theory for measures of tail risk
- Extremiles: A New Perspective on Asymmetric Least Squares
- Dynamic large financial networks \textit{via} conditional expected shortfalls
- On the properties of the lambda value at risk: robustness, elicitability and consistency
- Quantile-based risk sharing
- Backtesting VaR and expectiles with realized scores
- Order-sensitivity and equivariance of scoring functions
- Multivariate Shortfall Risk Allocation and Systemic Risk
- Correction to: ``Higher order elicitability and Osband's principle
- Dynamic semiparametric models for expected shortfall (and value-at-risk)
- Properization: constructing proper scoring rules via Bayes acts
- On joint marginal expected shortfall and associated contribution risk measures
- Comparing Predictive Accuracy in the Presence of a Loss Function Shape Parameter
- Realized Quantiles*
- Predicting the Global Minimum Variance Portfolio
- Backtesting Systemic Risk Forecasts Using Multi-Objective Elicitability
- Estimation of complier expected shortfall treatment effects with a binary instrumental variable
- Powerful Backtests for Historical Simulation Expected Shortfall Models
- Risk quantization by magnitude and propensity
- Loss function-based change point detection in risk measures
- Inference for joint quantile and expected shortfall regression
- Sequential testing for elicitable functionals via supermartingales
- Regression diagnostics meets forecast evaluation: conditional calibration, reliability diagrams, and coefficient of determination
- Multiple measures realized GARCH models
- Assessing the accuracy of exponentially weighted moving average models for Value-at-Risk and Expected Shortfall of crypto portfolios
- Modelling additive extremile regression by iteratively penalized least asymmetric weighted squares and gradient descent boosting
- Two-step online estimation and inference for expected shortfall regression with streaming data
- Elicitability of Instance and Object Ranking
- Better the devil you know: improved forecasts from imperfect models
- Time-varying parameters realized GARCH models for tracking attenuation bias in volatility dynamics
- Review of statistical approaches for modeling high-frequency trading data
- Sensitivity measures based on scoring functions
- Range-based risk measures and their applications
- Osband's Principle for Identification Functions
- Forecasting Value at Risk and Expected Shortfall Using a Semiparametric Approach Based on the Asymmetric Laplace Distribution
- Backtestability and the ridge backtest
- Uncertainty Comparison Between Value-at-Risk and Expected Shortfall
- Estimation and backtesting of risk measures with emphasis on distortion risk measures
This page was built for publication: Higher order elicitability and Osband's principle
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q309736)
