Proving prediction prudence

@article{Tasche2020ProvingPP,
  title={Proving prediction prudence},
  author={D. Tasche},
  journal={arXiv: Risk Management},
  year={2020}
}
  • D. Tasche
  • Published 2020
  • Mathematics, Economics
  • arXiv: Risk Management
  • We study how to perform tests on samples of pairs of observations and predictions in order to assess whether or not the predictions are prudent. Prudence requires that that the mean of the difference of the observation-prediction pairs can be shown to be significantly negative. For safe conclusions, we suggest testing both unweighted (or equally weighted) and weighted means and explicitly taking into account the randomness of individual pairs. The test methods presented are mainly specified as… CONTINUE READING

    References

    SHOWING 1-10 OF 17 REFERENCES
    Bootstrap Methods and Their Application
    • 1,485
    The Law of Total Odds
    • 3
    • PDF
    The Art of Probability-of-Default Curve Calibration
    • 14
    • PDF
    Objective Bayesian estimation of the probability of default
    • 6
    • Highly Influential
    Introduction to Probability and Statistics.
    • 1,002
    • Highly Influential
    Probability and Statistics
    • 2,451
    Construction and Assessment of Classification Rules
    • M. Wade
    • Mathematics, Computer Science
    • Technometrics
    • 1999
    • 244