Disaggregated evaluation across subgroups is critical for assessing the fairness of machine learning models, but its uncritical use can mislead practitioners. We show that equal performance across subgroups is an unreliable measure of fairness when data are representative of the relevant populations but reflective of real-world disparities. Furthermore, when data are not representative due to selection bias, both disaggregated evaluation and alternative approaches based on conditional independence testing may be invalid without explicit assumptions regarding the bias mechanism. We use causal graphical models to predict metric stability across subgroups under different data generating processes. Our framework suggests complementing disaggregated evaluations with explicit causal assumptions and analysis to control for confounding and distribution shift, including conditional independence testing and weighted performance estimation. These findings have broad implications for how practitioners design and interpret model assessments given the ubiquity of disaggregated evaluation.
View on arXiv@article{pfohl2025_2506.04193,
title={ Understanding challenges to the interpretation of disaggregated evaluations of algorithmic fairness },
author={ Stephen R. Pfohl and Natalie Harris and Chirag Nagpal and David Madras and Vishwali Mhasawade and Olawale Salaudeen and Awa Dieng and Shannon Sequeira and Santiago Arciniegas and Lillian Sung and Nnamdi Ezeanochie and Heather Cole-Lewis and Katherine Heller and Sanmi Koyejo and Alexander DÁmour },
journal={arXiv preprint arXiv:2506.04193},
year={ 2025 }
}