English

Failure of Calibration is Typical

Statistics Theory 2013-06-21 v1 Machine Learning Statistics Theory

Abstract

Schervish (1985b) showed that every forecasting system is noncalibrated for uncountably many data sequences that it might see. This result is strengthened here: from a topological point of view, failure of calibration is typical and calibration rare. Meanwhile, Bayesian forecasters are certain that they are calibrated---this invites worries about the connection between Bayesianism and rationality.

Cite

@article{arxiv.1306.4943,
  title  = {Failure of Calibration is Typical},
  author = {Gordon Belot},
  journal= {arXiv preprint arXiv:1306.4943},
  year   = {2013}
}

Comments

Forthcoming in Statistics and Probability Letters

R2 v1 2026-06-22T00:37:41.782Z