Reasonable uncertainty: Confidence intervals in empirical Bayes discrimination detection

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Gu, Jiaying, Ignatiadis, Nikolaos, Shaikh, Azeem M.
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908493205733376
author Gu, Jiaying
Ignatiadis, Nikolaos
Shaikh, Azeem M.
author_facet Gu, Jiaying
Ignatiadis, Nikolaos
Shaikh, Azeem M.
contents We revisit empirical Bayes discrimination detection, focusing on uncertainty arising from both partial identification and sampling variability. While prior work has mostly focused on partial identification, we find that some empirical findings are not robust to sampling uncertainty. To better connect statistical evidence to the magnitude of real-world discriminatory behavior, we propose a counterfactual odds-ratio estimand with a attractive properties and interpretation. Our analysis reveals the importance of careful attention to uncertainty quantification and downstream goals in empirical Bayes analyses.
format Preprint
id arxiv_https___arxiv_org_abs_2508_13110
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Reasonable uncertainty: Confidence intervals in empirical Bayes discrimination detection
Gu, Jiaying
Ignatiadis, Nikolaos
Shaikh, Azeem M.
Econometrics
Methodology
We revisit empirical Bayes discrimination detection, focusing on uncertainty arising from both partial identification and sampling variability. While prior work has mostly focused on partial identification, we find that some empirical findings are not robust to sampling uncertainty. To better connect statistical evidence to the magnitude of real-world discriminatory behavior, we propose a counterfactual odds-ratio estimand with a attractive properties and interpretation. Our analysis reveals the importance of careful attention to uncertainty quantification and downstream goals in empirical Bayes analyses.
title Reasonable uncertainty: Confidence intervals in empirical Bayes discrimination detection
topic Econometrics
Methodology
url https://arxiv.org/abs/2508.13110