EconBase
← All papers

Inference for an Algorithmic Fairness-Accuracy Frontier

Yiqi Liu, Francesca Molinari

arXiv 14 Feb 2024 · Econometrics · 2 citations (OpenAlex)

arXiv:2402.08879 · PDF · DOI · OpenAlex · Extracted main text

Abstract

Algorithms are increasingly used to aid with high-stakes decision making. Yet, their predictive ability frequently exhibits systematic variation across population subgroups. To assess the trade-off between fairness and accuracy using finite data, we propose a debiased machine learning estimator for the fairness-accuracy frontier introduced by Liang, Lu, Mu, and Okumura (2024). We derive its asymptotic distribution and propose inference methods to test key hypotheses in the fairness literature, such as (i) whether excluding group identity from use in training the algorithm is optimal and (ii) whether there are less discriminatory alternatives to a given algorithm. In addition, we construct an estimator for the distance between a given algorithm and the fairest point on the frontier, and characterize its asymptotic distribution. Using Monte Carlo simulations, we evaluate the finite-sample performance of our inference methods. We apply our framework to re-evaluate algorithms used in hospital care management and show that our approach yields alternative algorithms that lie on the fairness-accuracy frontier, offering improvements along both dimensions.

Citation extraction

55
references
163
in-text mentions
55
distinct cited
5
self-citations
35,404
main-text words

appendix boundary found by none_found · 100% of the source is main text. Read the extracted text to check this.

Most heavily cited references

The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.

ReferenceIntensityMentionsSectionsMain text
1Obermeyer, Ziad, Brian Powers, Christine Vogeli, and Sendhil Mullain… (2019) Dissecting racial bias in an algorithm used to manage the health of populations1.000254100%
2Liang, Annie, Jay Lu, Xiaosheng Mu, and Kyohei Okumura (2024) Algorithm Design: A Fairness-Accuracy Frontier1.000168100%
3Fang, Zheng and Andres Santos (2019) Inference on directionally differentiable functions1.000165100%
4Kaido, Hiroaki (2016) A dual approach to inference for partially identified econometric models1.000113100%
5Molchanov, Ilya and Francesca Molinari (2018) Random Sets in Econometrics self1.00084100%
6Semenova, Vira (2023) Debiased machine learning of set-identified linear models1.00075100%
7Beresteanu, Arie and Francesca Molinari (2008) Asymptotic Properties for a Class of Partially Identified Models self1.00053100%
8Chandrasekhar, Arun, Victor Chernozhukov, Francesca Molinari, and Pa… (2018) Best linear approximations to set identified functions: with an application to the gender wage gap self0.92843100%
9Cárcamo, Javier, Antonio Cuevas, and Luis-Alberto Rodríguez (2020) Directional differentiability for supremum-type functionals: Statistical applications0.87472100%
10Schneider, Rolf (1993) Convex Bodies: The Brunn-Minkowski Theory0.87452100%

Showing the top 10 of 55 scored citations.

Cited by, within the corpus

arXiv econ.EM papers that cite this one, ranked by how heavily they lean on it.

Citing paperIntensityMentionsSections
1Identification and Inference for Algorithmic Frontiers with Selective Labels1.000236
2Testing the Fairness-Accuracy Improvability of Algorithms0.51121
3Statistical Inference of Optimal Allocations 1: Regularities and their Implications0.40511
4On the Lower Confidence Band for the Optimal Welfare in Policy Learning0.40511
5Leave No One Undermined: Policy Targeting with Regret Aversion0.40511
6Training and Testing with Multiple Splits: A Central Limit Theorem for Split-Sample Estimators0.40511