# Representativeness in Statistics, Politics, and Machine Learning

arXiv: https://arxiv.org/abs/2101.03827 · HTML: https://mlsanity.com/paper/2101.03827/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jan 2021.

## Built on by (most cited first, 17 of 17)

- [Auditing large language models: a three-layered approach](https://mlsanity.com/paper/2302.08500/) (2023)
- [The Participatory Turn in AI Design: Theoretical Foundations and the Current State of Practice](https://mlsanity.com/paper/2310.00907/) (2023)
- [ImageNet-X: Understanding Model Mistakes with Factor of Variation Annotations](https://mlsanity.com/paper/2211.01866/) (2022)
- [Representation Matters: Assessing the Importance of Subgroup Allocations in Training Data](https://mlsanity.com/paper/2103.03399/) (2021)
- [The Case for "Thick Evaluations" of Cultural Representation in AI](https://mlsanity.com/paper/2503.19075/) (2025)
- [Scaling Laws Do Not Scale](https://mlsanity.com/paper/2307.03201/) (2023)
- [Towards a multi-stakeholder value-based assessment framework for algorithmic systems](https://mlsanity.com/paper/2205.04525/) (2022)
- [Measuring and signing fairness as performance under multiple stakeholder distributions](https://mlsanity.com/paper/2207.09960/) (2022)
- [Thinking Beyond Distributions in Testing Machine Learned Models](https://mlsanity.com/paper/2112.03057/) (2021)
- [Surveys Considered Harmful? Reflecting on the Use of Surveys in AI Research, Development, and Governance](https://mlsanity.com/paper/2408.01458/) (2024)
- [SoUnD Framework: Analyzing (So)cial Representation in (Un)structured (D)ata](https://mlsanity.com/paper/2311.17259/) (2023)
- [Analyzing and Mitigating Bias for Vulnerable Classes: Towards Balanced Representation in Dataset](https://mlsanity.com/paper/2401.10397/) (2024)
- [Unraveling the Interconnected Axes of Heterogeneity in Machine Learning for Democratic and Inclusive Advancements](https://mlsanity.com/paper/2306.10043/) (2023)
- [Constructing Enhanced Mutual Information for Online Class-Incremental Learning](https://mlsanity.com/paper/2407.18526/) (2024)
- [AI Thinking: A framework for rethinking artificial intelligence in practice](https://mlsanity.com/paper/2409.12922/) (2024)
- [Representative Ranking for Deliberation in the Public Sphere](https://mlsanity.com/paper/2503.18962/) (2025)
- [Normality and the Turing Test](https://mlsanity.com/paper/2508.21382/) (2025)

## Abstract (arXiv)

Representativeness is a foundational yet slippery concept. Though familiar at first blush, it lacks a single precise meaning. Instead, meanings range from typical or characteristic, to a proportionate match between sample and population, to a more general sense of accuracy, generalizability, coverage, or inclusiveness. Moreover, the concept has long been contested. In statistics, debates about the merits and methods of selecting a representative sample date back to the late 19th century; in politics, debates about the value of likeness as a logic of political representation are older still. Today, as the concept crops up in the study of fairness and accountability in machine learning, we need to carefully consider the term's meanings in order to communicate clearly and account for their normative implications. In this paper, we ask what representativeness means, how it is mobilized socially, and what values and ideals it communicates or confronts. We trace the concept's history in statistics and discuss normative tensions concerning its relationship to likeness, exclusion, authority, and aspiration. We draw on these analyses to think through how representativeness is used in FAccT debates, with emphasis on data, shift, participation, and power.