EUVIMEDEUVIMED entdecken
Open Access

Deconfounded‐Debiased Estimation and Inference for High‐Dimensional Mediation Analysis With Pervasive Hidden Confounders

Zhaoyang Li iD, Lulu Pan, Yongfu Yu iD, Guoyou Qin iD, Bo Fu iD

Statistics in Medicine · 2026

DOI: 10.1002/sim.70741 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Statistics in Medicine, 2026. Verfasst von Zhaoyang Li und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biostatistics, School of Public Health, Fudan University, Shanghai, China. Hauptthemen laut MEDLINE: Mediation Analysis. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Shanghai Municipal Science and Technology Major Project, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Mediation analysis is a powerful tool for elucidating the causal mechanisms by which exposures influence outcomes through mediators. However, conventional approaches often yield biased estimates of mediation effects in scenarios involving high‐dimensional exposures and high‐dimensional mediators, alongside a small number of pervasive hidden confounders that simultaneously affect the exposures, mediators, and outcome or the exposures and outcome. To address these challenges, we propose a deconfounded‐debiased method for estimation and inference in high‐dimensional mediation analysis based on the difference‐in‐coefficients strategy. This approach effectively corrects biases arising from both pervasive hidden confounders and high‐dimensionality without requiring prior knowledge of hidden confounders or a sparse precision matrix assumption. We establish the asymptotic normality of the proposed estimators for both direct and indirect effects, and develop hypothesis testing procedures that asymptotically achieve validity and power lower bounds. Simulation experiments demonstrate our method's superior finite‐sample performance in both estimation and inference, especially in the presence of pervasive hidden confounding. We also apply the proposed method to real data from the Alzheimer's Disease Neuroimaging Initiative to identify serum metabolites that influence Alzheimer's disease progression through DNA methylation pathways.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Mediation AnalysisHumansAlzheimer DiseaseComputer SimulationConfounding Factors, EpidemiologicBiasModels, StatisticalDNA MethylationCausalityNeuroimagingData Interpretation, Statistical

Stichwörter der Autor:innen

debiasingdeconfoundinghigh‐dimensional mediation analysispervasive hidden confoundersspectral transformation

Autor:innen und Institutionen

  • Department of Biostatistics, School of Public Health, Fudan University, Shanghai, China.
  • Department of Biostatistics, Shanghai Stomatological Hospital & School of Public Health, Fudan University, Shanghai, China.
  • Shanghai Institute of Infectious Disease and Biosecurity, School of Public Health, Fudan University, Shanghai, China.
  • School of Data Science, Fudan University, Shanghai, China.

ORCID-Profile: Zhaoyang Li, Yongfu Yu, Guoyou Qin, Bo Fu

Förderung

  • Shanghai Municipal Science and Technology Major Project
  • National Natural Science Foundation of China

Zitieren

APA

Li, Z., Pan, L., Yu, Y., Qin, G., & Fu, B. (2026). Deconfounded‐Debiased Estimation and Inference for High‐Dimensional Mediation Analysis With Pervasive Hidden Confounders. Statistics in Medicine. https://doi.org/10.1002/sim.70741

Vancouver

Li Z, Pan L, Yu Y, Qin G, Fu B. Deconfounded‐Debiased Estimation and Inference for High‐Dimensional Mediation Analysis With Pervasive Hidden Confounders. Statistics in Medicine. 2026. doi:10.1002/sim.70741

BibTeX
@article{Li2026,
  author = {Li, Zhaoyang and Pan, Lulu and Yu, Yongfu and Qin, Guoyou and Fu, Bo},
  title = {Deconfounded‐Debiased Estimation and Inference for High‐Dimensional Mediation Analysis With Pervasive Hidden Confounders},
  journal = {Statistics in Medicine},
  year = {2026},
  doi = {10.1002/sim.70741}
}
Kostenlos starten →