CoChat
Sign Up
Cited by 50Ethics and Social Impacts of AIExplainable Artificial Intelligence (XAI)Imbalanced Data Classification Techniques

Measuring the Biases that Matter: The Ethical and Casual Foundations for Measures of Fairness in Algorithms

Glymour, Bruce, Herington, Jonathan·2019·Proceedings of the Conference on Fairness, Accountability, and Transparency
DOI 10.1145/3287560.3287573
Open this paper in CoChat — free account

Abstract

Measures of algorithmic bias can be roughly classified into four categories, distinguished by the conditional probabilistic dependencies to which they are sensitive. First, measures of "procedural bias" diagnose bias when the score returned by an algorithm is probabilistically dependent on a sensitive class variable (e.g. race or sex). Second, measures of "outcome bias" capture probabilistic dependence between class variables and the outcome for each subject (e.g. parole granted or loan denied). Third, measures of "behavior-relative error bias" capture probabilistic dependence between class variables and the algorithmic score, conditional on target behaviors (e.g. recidivism or loan default). Fourth, measures of "score-relative error bias" capture probabilistic dependence between class variables and behavior, conditional on score. Several recent discussions have demonstrated a tradeoff between these different measures of algorithmic bias, and at least one recent paper has suggested conditions under which tradeoffs may be minimized.

Integrity signals

Registry

Crossref · 10.1145/3287560.3287573

Cites

32 of 32 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Fairness researchers have begun to investigate graph-and network-based methods for discovering proxies.

    “More recently, fairness researchers have begun to investigate graph-and network-based methods for discovering proxies either with respect to anonymity criteria (e.g.[301]) or speciic notions of fairness (we introduce these approaches in subsection 4.2).”

    From Fairness in machine learning: A survey (2024) · cites this paper as [118]

  • Causal methods are specifically well suited to identifying proxies of sensitive variables.

    “Thus, causal methods are speciically well suited to identifying 1) proxies of sensitive variables as discussed in subsection 2.1; 2) which subgroups are most (un)fairly treated and diferentiate the types of bias exhibited [118]; and 3) provide transparency with respect to how (classiication) decisions were made [143].”

    From Fairness in machine learning: A survey (2024) · cites this paper as [118]

  • Causal methods are specifically well suited to identifying which subgroups are most (un)fairly treated and differentiating the types of bias exhibited.

    “Thus, causal methods are speciically well suited to identifying 1) proxies of sensitive variables as discussed in subsection 2.1; 2) which subgroups are most (un)fairly treated and diferentiate the types of bias exhibited [118]; and 3) provide transparency with respect to how (classiication) decisions were made [143].”

    From Fairness in machine learning: A survey (2024) · cites this paper as [118]

Cites

Flagged first, then by citations

Cited by

Sorted by citations

Related

Authors
Glymour, B., & Herington, J.
Affiliations
Kansas State University (US)
ORCID
Herington, Jonathan
Venue
Proceedings of the Conference on Fairness, Accountability, and Transparency
Publisher
ACM
Published
2019-01-29
Pages
269-278
DOI
10.1145/3287560.3287573
OpenAlex
W2908730746
Cited by
50
References
32
Citations by year
2026: 2 · 2025: 4 · 2024: 4 · 2023: 8 · 2022: 9 · 2021: 13 · 2020: 9 · 2019: 1
FWCI
8.35
Type
conference paper
Language
en
Open access
closed
Licence
www.acm.org/publications/policies/copyright_policy#Background (vor)
Locations
ACM Conference on Fairness, Accountability, and Transparency (FAccT) (publishedVersion)
Funders
Kansas State University
Topics
  • Social Sciences › Safety Research › Ethics and Social Impacts of AI
  • Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
  • Physical Sciences › Computer Science › Artificial Intelligence › Imbalanced Data Classification Techniques
Keywords
algorithmic bias, bias measurement, outcome bias, sensitive attributes

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