---
title: "Calibration within groups"
description: "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."
canonical: https://aigovernanceengineer.com/glossary/calibration-within-groups
author: "Jorge García Aibar"
license: "CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)"
doi: https://doi.org/10.5281/zenodo.22956197
version: "0.5.0"
updated: 2026-09-24
---

# Calibration within groups

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](https://aigovernanceengineer.com/bok/fairness-and-explainability#the-impossibility-results)
- Chapters: [ch. 16, Fairness & XAI](https://aigovernanceengineer.com/bok/fairness-and-explainability)
- Contrast with: [Calibration](https://aigovernanceengineer.com/glossary/calibration) · [Equalised odds](https://aigovernanceengineer.com/glossary/equalised-odds)
- In the glossary chapter: https://aigovernanceengineer.com/bok/glossary#t-calibration-within-groups

## Sources

[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)