THE FOUR-FIFTHS RULE FOR ASSESSING ADVERSE IMPACT: AN ARITHMETIC, INTUITIVE, AND LOGICAL ANALYSIS OF THE RULE AND IMPLICATIONS FOR FUTURE RESEARCH AND PRACTICE
Abstract
Evidence for adverse impact in applied, organizational settings can often depend on application of the “four-fifths rule.” We analyze the arithmetic four-fifths rule, its operationalization, and related statistical tests. We note that the rule has intuitive appeal and has arithmetic directness. On the other hand, the four-fifths rule contains many ambiguities because of the manner in which it is defined, as well as its use in practice. One purpose of this article is to discuss the arithmetic and statistical facets of the definition. A related purpose of this article is to demonstrate where the ambiguities (and possibly unintended consequences) with the four-fifths rule might arise when numerical interpretations are invoked. Implications for future research and academic dialogues are then noted.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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?
The four-fifths rule establishes a baseline against which impermissible discriminatory outcomes can be identified by comparing relative rates of selection between demographic groups.
“The four-fifths rule establishes a baseline against which impermissible discriminatory outcomes (aka 'disparate impact') can be identified by comparing relative rates of selection between demographic groups.”
From Null Compliance: NYC Local Law 144 and the challenges of algorithm accountability (2024) · cites this paper as [3]
The four-fifths rule is not genuinely a rule or law; it is best described as a rule of thumb or convention that is ingrained in hiring practices, and employers and developers are highly incentivized to reduce potential scrutiny by targeting that threshold.
“The four-fifths rule is not genuinely a rule or law; it is best described as a rule of thumb or convention that is ingrained in hiring practices, and employers and developers are highly incentivized to reduce potential scrutiny by targeting that threshold.”
From Null Compliance: NYC Local Law 144 and the challenges of algorithm accountability (2024) · cites this paper as [3]
If the less-selected group's selection rate falls below four-fifths (80%) of the baseline then there is a presumption that disparate impact may be occurring and warrants further investigation, typically through a complaint to the EEOC.
“If the less-selected group's selection rate falls below four-fifths (80%) of the baseline then there is a presumption that disparate impact may be occurring and warrants further investigation, typically through a complaint to the EEOC.”
From Null Compliance: NYC Local Law 144 and the challenges of algorithm accountability (2024) · cites this paper as [3]
The four-fifths rule is a general guideline that an impact ratio greater than 0.8 is considered de facto evidence (but not de jure evidence) of non-discriminatory outcomes.
“The 'four-fifths rule' is a general guideline that an impact ratio greater than 0.8 is considered de facto evidence (but not de jure evidence) of non-discriminatory outcomes.”
From Null Compliance: NYC Local Law 144 and the challenges of algorithm accountability (2024) · cites this paper as [3]
Cites
The interpretation of interaction in contingency tables
Simpson, E. H. (1951) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1951.tb00088.x · Cited by 2,301 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Null Compliance: NYC Local Law 144 and the challenges of algorithm accountability
Wright, L., Muenster, R. M., Vecchione, B., Qu, T., Cai, P. (., Smith, A., Comm 2450 Student Investigators, Metcalf, J., & Matias, J. N. (2024) · The 2024 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3630106.3658998 · Cited by 43 · see citing works
“The so-called ‘four-fifths rule’ [3, 50, 69] that emerged from US federal anti-discrimination regulations and jurisprudence looms large in employment discrimination and algorithmic fairness (see Appendix for key terms and historical details).”
BackgroundNull Compliance: NYC Local Law 144 and the Challenges of Algorithm Accountability
Wright, L., Muenster, R. M., Vecchione, B., Qu, T., Pika, Cai, Investigators, C. 2. S., Metcalf, J., & Matias, J. N. (2024) · arXiv · doi:10.48550/arxiv.2406.01399 · Cited by 43
Lewicki, K., Lee, M. S. A., Cobbe, J., & Singh, J. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581463 · Cited by 30 · see citing works
“Equal Employment Opportunity Commission (EEOC) Uniform Guidelines 4/5ths rule [19].”
Background
- Authors
- Bobko, P., & Roth, P. L.
- Venue
- Research in Personnel and Human Resources Management
- Publisher
- Emerald (MCB UP )
- Published
- 2004-06-09
- Pages
- 177-198
- ISSN
- 0742-7301 (ISSN-L)
- OpenAlex
- W2497210133
- Cited by
- 26
- References
- 1
- Citations by year
- 2026: 1 · 2024: 1 · 2023: 3 · 2022: 6 · 2021: 1 · 2019: 1 · 2018: 1 · 2017: 1 · 2015: 3 · 2014: 1 · 2013: 1
- FWCI
- 2.98
- Type
- book chapter
- Language
- en
- Open access
- closed
- Locations
- Research in personnel and human resources management (publishedVersion)
- Topics
- Social Sciences › Decision Sciences › Management Science and Operations Research › Psychometric Methodologies and Testing
- Social Sciences › Law › Discrimination and Equality Law
- Social Sciences › Business, Management and Accounting › Organizational Behavior and Human Resource Management › Employer Branding and e-HRM
- Keywords
- adverse impact, personnel selection, job applicants, operationalization, numerical interpretation
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
