Mediation analysis with unmeasured confounding between parallel mediators and outcome

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Shuai, Kang, Liu, Lan, He, Yangbo, Li, Wei
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911549093838848
author Shuai, Kang
Liu, Lan
He, Yangbo
Li, Wei
author_facet Shuai, Kang
Liu, Lan
He, Yangbo
Li, Wei
contents Mediation analysis extending beyond single mediators has gained significant attention in recent years. However, related methods often assume the absence of unmeasured mediator-outcome confounding. To address this, we develop a mediation analysis framework that accounts for such confounding within a linear structural equation model with parallel mediators. Specifically, we introduce a pseudo proxy variable to capture unmeasured confounding, allowing us to identify causal parameters. Leveraging this proxy, we propose a partially penalized method to identify mediators that significantly affect the outcome. The resultant estimates are consistent, and the estimates of nonzero parameters are asymptotically normal. Motivated by these results, we further introduce a procedure that can consistently select active mediation pathways with large probability. Simulation studies demonstrate the superior performance of the proposed approach. Finally, we apply our approach to genomic data, identifying gene expressions that potentially mediate the impact of a genetic variant on mouse obesity.
format Preprint
id arxiv_https___arxiv_org_abs_2311_16793
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Mediation analysis with unmeasured confounding between parallel mediators and outcome
Shuai, Kang
Liu, Lan
He, Yangbo
Li, Wei
Methodology
Mediation analysis extending beyond single mediators has gained significant attention in recent years. However, related methods often assume the absence of unmeasured mediator-outcome confounding. To address this, we develop a mediation analysis framework that accounts for such confounding within a linear structural equation model with parallel mediators. Specifically, we introduce a pseudo proxy variable to capture unmeasured confounding, allowing us to identify causal parameters. Leveraging this proxy, we propose a partially penalized method to identify mediators that significantly affect the outcome. The resultant estimates are consistent, and the estimates of nonzero parameters are asymptotically normal. Motivated by these results, we further introduce a procedure that can consistently select active mediation pathways with large probability. Simulation studies demonstrate the superior performance of the proposed approach. Finally, we apply our approach to genomic data, identifying gene expressions that potentially mediate the impact of a genetic variant on mouse obesity.
title Mediation analysis with unmeasured confounding between parallel mediators and outcome
topic Methodology
url https://arxiv.org/abs/2311.16793