Forecaster's Dilemma: Extreme Events and Forecast Evaluation

@article{Lerch2015ForecastersDE,
  title={Forecaster's Dilemma: Extreme Events and Forecast Evaluation},
  author={S. Lerch and T. Thorarinsdottir and F. Ravazzolo and T. Gneiting},
  journal={arXiv: Methodology},
  year={2015}
}
  • S. Lerch, T. Thorarinsdottir, +1 author T. Gneiting
  • Published 2015
  • Computer Science, History, Mathematics
  • arXiv: Methodology
  • In public discussions of the quality of forecasts, attention typically focuses on the predictive performance in cases of extreme events. However, the restriction of conventional forecast evaluation methods to subsets of extreme observations has unexpected and undesired effects, and is bound to discredit skillful forecasts when the signal-to-noise ratio in the data generating process is low. Conditioning on outcomes is incompatible with the theoretical assumptions of established forecast… CONTINUE READING
    62 Citations
    Focusing on regions of interest in forecast evaluation
    • 7
    • Highly Influenced
    • PDF
    Scoring rules for simple forecasting models: The case of Cyprus GDP and its sectors
    • 1
    • Highly Influenced
    • PDF
    Interpretation of point forecasts with unkown directive
    • 2
    • PDF
    Extreme events evaluation using CRPS distributions
    • 2
    • Highly Influenced
    • PDF
    Score decompositions in forecast verification
    Probabilistic predictive analysis of business cycle fluctuations in Polish economy
    • 4
    • PDF
    Proper scoring rules for evaluating asymmetry in density forecasting
    • PDF

    References

    SHOWING 1-10 OF 89 REFERENCES
    The Forecaster's Dilemma
    • 16
    • PDF
    Cross-calibration of probabilistic forecasts
    • 20
    • Highly Influential
    • PDF
    The extreme dependency score: a non‐vanishing measure for forecasts of rare events
    • 106
    • PDF
    The role of the information set for forecasting—with applications to risk management
    • 39
    • PDF
    Making and Evaluating Point Forecasts
    • 611
    • PDF
    Probabilistic forecasts, calibration and sharpness
    • 1,033
    • PDF
    A comparison of ensemble post-processing methods for extreme events
    • 39
    • PDF
    Comparing Density Forecasts via Weighted Likelihood Ratio Tests
    • 460
    • Highly Influential
    • PDF
    Comparing Density Forecasts Using Threshold- and Quantile-Weighted Scoring Rules
    • 251
    • PDF