Measurement and Fairness

Abstract

We propose measurement modeling from the quantitative social sciences as a framework for understanding fairness in computational systems. Computational systems often involve unobservable theoretical constructs, such as socioeconomic status, teacher effectiveness, and risk of recidivism. Such constructs cannot be measured directly and must instead be inferred from measurements of observable properties (and other unobservable theoretical constructs) thought to be related to them -- i.e., operationalized via a measurement model. This process, which necessarily involves making assumptions, introduces the potential for mismatches between the theoretical understanding of the construct purported to be measured and its operationalization. We argue that many of the harms discussed in the literature on fairness in computational systems are direct results of such mismatches. We show how some of these harms could have been anticipated and, in some cases, mitigated if viewed through the lens of measurement modeling. To do this, we contribute fairness-oriented conceptualizations of construct reliability and construct validity that unite traditions from political science, education, and psychology and provide a set of tools for making explicit and testing assumptions about constructs and their operationalizations. We then turn to fairness itself, an essentially contested construct that has different theoretical understandings in different contexts. We argue that this contestedness underlies recent debates about fairness definitions: although these debates appear to be about different operationalizations, they are, in fact, debates about different theoretical understandings of fairness. We show how measurement modeling can provide a framework for getting to the core of these debates.

arXiv comment11 pages, 1 figure. To be published in the proceedings of the ACM Conference on Fairness, Accountability, and Transparency (FAccT '21)

References in corpus (3)

• Towards a Critical Race Methodology in Algorithmic Fairness
• Problem Formulation and Fairness
• The Profiling Potential of Computer Vision and the Challenge of Computational Empiricism

Cited by in corpus (43)

• The Fallacy of AI Functionality
• Auditing large language models: a three-layered approach
• Harms from Increasingly Agentic Algorithmic Systems
• Building Human Values into Recommender Systems: An Interdisciplinary Synthesis
• Seeing Like a Toolkit: How Toolkits Envision the Work of AI Ethics
• Algorithms and Decision-Making in the Public Sector
• Fairness and Bias in Algorithmic Hiring: a Multidisciplinary Survey
• Escaping the Impossibility of Fairness: From Formal to Substantive Algorithmic Fairness
• Collective Constitutional AI: Aligning a Language Model with Public Input
• Can Workers Meaningfully Consent to Workplace Wellbeing Technologies?
• The worst of both worlds: A comparative analysis of errors in learning from data in psychology and machine learning
• A Scoping Study of Evaluation Practices for Responsible AI Tools: Steps Towards Effectiveness Evaluations
• A Systematic Review of Ethical Concerns with Voice Assistants
• Algorithmic Unfairness through the Lens of EU Non-Discrimination Law: Or Why the Law is not a Decision Tree
• Evaluating Proposed Fairness Models for Face Recognition Algorithms
• Model Sketching: Centering Concepts in Early-Stage Machine Learning Model Design
• Augmented Datasheets for Speech Datasets and Ethical Decision-Making
• Justice in Misinformation Detection Systems: An Analysis of Algorithms, Stakeholders, and Potential Harms
• Toward Operationalizing Pipeline-aware ML Fairness: A Research Agenda for Developing Practical Guidelines and Tools
• Specification Overfitting in Artificial Intelligence
• The Value-Sensitive Conversational Agent Co-Design Framework
• The Fall of an Algorithm: Characterizing the Dynamics Toward Abandonment
• An Empirical Analysis of Racial Categories in the Algorithmic Fairness Literature
• Multi-Target Multiplicity: Flexibility and Fairness in Target Specification under Resource Constraints
• A Method to Analyze Multiple Social Identities in Twitter Bios
• Counterfactual Prediction Under Outcome Measurement Error
• The Role of Relevance in Fair Ranking
• Optimization's Neglected Normative Commitments
• The Neutrality Fallacy: When Algorithmic Fairness Interventions are (Not) Positive Action
• Making the Right Thing: Bridging HCI and Responsible AI in Early-Stage AI Concept Selection
• Making Intelligence: Ethical Values in IQ and ML Benchmarks
• Forks Over Knives: Predictive Inconsistency in Criminal Justice Algorithmic Risk Assessment Tools
• Technology as uncharted territory: Contextual integrity and the notion of AI as new ethical ground
• Diverse Perspectives Can Mitigate Political Bias in Crowdsourced Content Moderation
• Patterns of gender-specializing query reformulation
• Group fairness without demographics using social networks
• Mapping Stakeholder Needs to Multi-Sided Fairness in Candidate Recommendation for Algorithmic Hiring
• From Model Performance to Claim: How a Change of Focus in Machine Learning Replicability Can Help Bridge the Responsibility Gap
• A Systematic Approach to Group Fairness in Automated Decision Making
• Tempo: Helping Data Scientists and Domain Experts Collaboratively Specify Predictive Modeling Tasks
• Policy Maps: Tools for Guiding the Unbounded Space of LLM Behaviors
• Perils of Label Indeterminacy: A Case Study on Prediction of Neurological Recovery After Cardiac Arrest
• Falsifying Discriminant Validity of Predictive Algorithms