AI Governance Engineer
GitHub

Calibration within groups

By Updated

The fairness property that, in every group, the people given a score s turn out positive at rate s, so a score means the same thing for everyone. It generally conflicts with equal error rates when base rates differ 1.

Developed in
ch. 16, The impossibility results
Chapters
ch. 16, Fairness & XAI
Contrast with
Calibration · Equalised odds
Source
1 numbered reference, listed below

Where it is used

One chapter of the Body of Knowledge uses the term. Each link opens the first section that does.

  • Fairness

    The property that a system's outcomes and errors do not unjustifiably disadvantage people or groups.

Sources

  1. [1] "Inherent Trade-Offs in the Fair Determination of Risk Scores" (Kleinberg, Mullainathan and Raghavan; three fairness conditions cannot hold together except in special cases; arXiv 1609.05807). arXiv. 2016-09-19. https://arxiv.org/abs/1609.05807 (verified: primary)

Definitions of legal terms paraphrase the cited text, which governs. Dated statements are as of .

Cite this term

García Aibar, J. (2026). Calibration within groups. In AI Governance Engineering: The Thesis & Body of Knowledge (v0.5.0), Glossary. https://doi.org/10.5281/zenodo.22956197. https://aigovernanceengineer.com/glossary/calibration-within-groups. CC BY 4.0

BibTeX

@misc{aige2026calibrationwithingroups,
  author  = {Jorge García Aibar},
  title   = {{Calibration within groups}},
  note    = {Glossary, AI Governance Engineering: The Thesis \& Body of Knowledge, version 0.5.0},
  year    = {2026},
  doi     = {10.5281/zenodo.22956197},
  url     = {https://aigovernanceengineer.com/glossary/calibration-within-groups}
}