On statistical criteria of algorithmic fairness
Open accessThe DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
Abstract
Predictive algorithms are playing an increasingly prominent role in society, being used to predict recidivism, loan repayment, job performance, and so on.With this increasing influence has come an increasing concern with the ways in which they might be unfair or biased against individuals in virtue of their race, gender, or, more generally, their group membership.Many purported criteria of algorithmic fairness concern statistical relationships between the algorithm's predictions and the actual outcomes, for instance requiring that the rate of false positives be equal across the relevant groups.We might seek to ensure that algorithms satisfy all of these purported fairness criteria.But a series of impossibility results shows that this is impossible, unless base rates are equal across the relevant groups.What are we to make of these pessimistic results?I argue that none of the purported criteria, except for a calibration criterion, are necessary conditions for fairness, on the grounds that they can all be simultaneously violated by a manifestly fair and uniquely optimal predictive algorithm, even when base rates are equal.I conclude with some general reflections on algorithmic fairness.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Epistemic Injustice: Power and the Ethics of Knowing
Fricker, M. (2007) · doi:10.1093/acprof:oso/9780198237907.001.0001 · Cited by 9,198
Dwork, C., Hardt, M., Pitassi, T., Reingold, O., & Zemel, R. (2012) · Proceedings of the 3rd Innovations in Theoretical Computer Science Conference · doi:10.1145/2090236.2090255 · Cited by 3,501
Equality of Opportunity in Supervised Learning
Hardt, M., Price, E., & Srebro, N. (2016) · arXiv · doi:10.48550/arxiv.1610.02413 · Cited by 2,536
Fair prediction with disparate impact: a study of bias in recidivism prediction instruments
Chouldechova, A. (2017) · Big Data · doi:10.1089/big.2016.0047 · Cited by 2,159 · cited 3×
“Chouldechova (2017) proves an analogous result for binary predictions, showing that no algorithm can satisfy (4), (5), and (6), again unless base rates are equal or the algorithm makes perfect predictions.”
BackgroundA Reductions Approach to Fair Classification
Agarwal, A., Beygelzimer, A., Dudík, M., Langford, J., & Wallach, H. (2018) · arXiv · doi:10.48550/arxiv.1803.02453 · Cited by 1,288
Algorithmic Decision Making and the Cost of Fairness
Corbett-Davies, S., Pierson, E., Feller, A., Goel, S., & Huq, A. (2017) · Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/3097983.3098095 · Cited by 1,149
Fairness in Criminal Justice Risk Assessments: The State of the Art
Berk, R., Heidari, H., Jabbari, S., Kearns, M., & Roth, A. (2021) · Sociological Methods & Research · doi:10.1177/0049124118782533 · Cited by 988 · cited 2×
“Mayson (2019) interprets them as showing that ‘Race neutrality is not attainable,’ and Berk et al. (2018) similarly conclude, ‘The implications of the impossibility results are huge...”
BackgroundInherent trade-offs in the fair determination of risk scores
Kleinberg, J., Mullainathan, S., & Raghavan, M. (2017) · Schloss Dagstuhl – Leibniz-Zentrum für Informatik · doi:10.4230/lipics.itcs.2017.43 · Cited by 943 · cited 6×
“This is the case, for example, in Agarwal et al. (2018), Berk et al. (2018), Corbett-Davies et al. (2017), Dwork et al. (2012), and Kleinberg et al. (2016).”
BackgroundInfluentialInherent Trade-Offs in the Fair Determination of Risk Scores
Kleinberg, J., Mullainathan, S., & Raghavan, M. (2016) · arXiv · doi:10.48550/arxiv.1609.05807 · Cited by 941
The Measure and Mismeasure of Fairness
Corbett-Davies, S., Gaebler, J. D., Nilforoshan, H., Shroff, R., & Goel, S. (2018) · arXiv · doi:10.48550/arxiv.1808.00023 · Cited by 444
Cited by
Moral consideration for AI systems by 2030
Sebo, J., & Long, R. (2025) · AI and Ethics · doi:10.1007/s43681-023-00379-1 · Cited by 80
Antidiscrimination Insurance Pricing: Regulations, Fairness Criteria, and Models
Xin, X., & Huang, F. (2024) · North American Actuarial Journal · doi:10.1080/10920277.2023.2190528 · Cited by 43
On the independence of association bias and empirical fairness in language models
Cabello, L., Jørgensen, A. K., & Søgaard, A. (2023) · 2023 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3593013.3594004 · Cited by 14
ACROCPoLis: A Descriptive Framework for Making Sense of Fairness
Aler Tubella, A., Coelho Mollo, D., Dahlgren Lindström, A., Devinney, H., Dignum, V., Ericson, P., Jonsson, A., Kampik, T., Lenaerts, T., Mendez, J. A., et al. (2023) · 2023 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3593013.3594059 · Cited by 8
“Several statistical operationalizations of fairness, often called “definitions”, have been developed, defended, and criticized, each hinging on different statistical features of the predictions produced by algorithms as criterial for fairness: [29], for instance, identifies 13 different operationalizations (see also […”
BackgroundAlgorithmic bias, generalist models, and clinical medicine
Keeling, G. (2024) · AI and Ethics · doi:10.1007/s43681-023-00329-x · Cited by 5
Metadata
- Authors
- Hedden, B.
- Venue
- Philosophy & Public Affairs
- Publisher
- Wiley
- Published
- 2021-03
- Volume
- 49
- Issue
- 2
- Pages
- 209-231
- ISSN
- 0048-3915 (ISSN-L)
- 1088-4963
- OpenAlex
- W3152256433
- Cited by
- 135
- References
- 11
- FWCI
- 31.20
- Type
- journal article
- Language
- en
- Open access
- bronze
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.