Abstract: We propose notions of calibration for probabilistic forecasts of general multivariate quantities. Probabilistic copula calibration is a natural analogue of probabilistic calibration in the univariate setting. It can be assessed empirically by checking for the uniformity of the copula probability integral transform (CopPIT), which is invariant under coordinate permutations and coordinatewise strictly monotone transformations of the predictive distribution and the outcome. The CopPIT histogram can be interpreted as a generalization and variant of the multivariate rank histogram, which has been used to check the calibration of ensemble forecasts. Climatological copula calibration is an analogue of marginal calibration in the univariate setting. Methods and tools are illustrated in a simulation study and applied to compare raw numerical model and statistically postprocessed ensemble forecasts of bivariate wind vectors.
Recommendations
- Assessing probabilistic forecasts of multivariate quantities, with an application to ensemble predictions of surface winds
- Probabilistic Forecasts, Calibration and Sharpness
- Calibration tests for multivariate Gaussian forecasts
- Cross-calibration of probabilistic forecasts
- A score regression approach to assess calibration of continuous probabilistic predictions
Cites work
- An introduction to copulas.
- Assessing probabilistic forecasts of multivariate quantities, with an application to ensemble predictions of surface winds
- Bivariate extreme value theory: Models and estimation
- Combining predictive distributions
- Ensemble forecasting
- Inference in multivariate Archimedean copula models
- Kendall distribution functions.
- Multivariate Archimedean copulas, \(d\)-monotone functions and \(\ell _{1}\)-norm symmetric distributions
- On Kendall's process
- On the distributional transform, Sklar's theorem, and the empirical copula process
- Out-of-sample comparison of copula specifications in multivariate density forecasts
- Predictive model assessment for count data
- Present Position and Potential Developments: Some Personal Views: Statistical Theory: The Prequential Approach
- Probabilistic Forecasts, Calibration and Sharpness
- Projection pursuit
- Remarks on a Multivariate Transformation
- Strictly Proper Scoring Rules, Prediction, and Estimation
- Unbiased risk estimation and scoring rules
- Uncertainty quantification in complex simulation models using ensemble copula coupling
- Wind energy: forecasting challenges for its operational management
Cited in
(10)- Rejoinder on: Assessing probabilistic forecasts of multivariate quantities, with an application to ensemble predictions of surface winds
- Calibration of the bulk and extremes of spatial data
- Calibration tests for multivariate Gaussian forecasts
- The joint valibration model in probabilistic weather forecasting: some preliminary issues
- Sequentially valid tests for forecast calibration
- Physically coherent probabilistic weather forecasts using multivariate discrete copula-based ensemble postprocessing methods
- Multivariate and spatial ensemble postprocessing methods
- Uncertainty quantification in complex simulation models using ensemble copula coupling
- Cross-calibration of probabilistic forecasts
- Assessing probabilistic forecasts of multivariate quantities, with an application to ensemble predictions of surface winds
This page was built for publication: Copula calibration
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q485915)
