Sensitivity Analysis of the Consistency Assumption

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Knaeble, Brian, Lin, Qinyun, Kummerfeld, Erich, Frank, Kenneth A.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915694019346432
author Knaeble, Brian
Lin, Qinyun
Kummerfeld, Erich
Frank, Kenneth A.
author_facet Knaeble, Brian
Lin, Qinyun
Kummerfeld, Erich
Frank, Kenneth A.
contents Sensitivity analysis informs causal inference by assessing the sensitivity of conclusions to departures from assumptions. The consistency assumption states that there are no hidden versions of treatment and that the outcome arising naturally equals the outcome arising from intervention. When reasoning about the possibility of consistency violations, it can be helpful to distinguish between covariates and versions of treatment. In the context of surgery, for example, genomic variables are covariates and the skill of a particular surgeon is a version of treatment. There may be hidden versions of treatment, and this paper addresses that concern with a new kind of sensitivity analysis. Whereas many methods for sensitivity analysis are focused on confounding by unmeasured covariates, the methodology of this paper is focused on confounding by hidden versions of treatment. In this paper, new mathematical notation is introduced to support the novel method, and example applications are described.
format Preprint
id arxiv_https___arxiv_org_abs_2512_21379
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Sensitivity Analysis of the Consistency Assumption
Knaeble, Brian
Lin, Qinyun
Kummerfeld, Erich
Frank, Kenneth A.
Methodology
Machine Learning
Optimization and Control
62D20, 62B15, 62H17, 62P99
Sensitivity analysis informs causal inference by assessing the sensitivity of conclusions to departures from assumptions. The consistency assumption states that there are no hidden versions of treatment and that the outcome arising naturally equals the outcome arising from intervention. When reasoning about the possibility of consistency violations, it can be helpful to distinguish between covariates and versions of treatment. In the context of surgery, for example, genomic variables are covariates and the skill of a particular surgeon is a version of treatment. There may be hidden versions of treatment, and this paper addresses that concern with a new kind of sensitivity analysis. Whereas many methods for sensitivity analysis are focused on confounding by unmeasured covariates, the methodology of this paper is focused on confounding by hidden versions of treatment. In this paper, new mathematical notation is introduced to support the novel method, and example applications are described.
title Sensitivity Analysis of the Consistency Assumption
topic Methodology
Machine Learning
Optimization and Control
62D20, 62B15, 62H17, 62P99
url https://arxiv.org/abs/2512.21379