Targeted maximum likelihood estimation for mediation analysis with multiple time-varying mediators
Biometrics · 09.04.2026 · 82 (2)
DOI: 10.1093/biomtc/ujag102 ↗Kurz gefasst
Fachartikel in der Zeitschrift Biometrics, online erschienen am 08.06.2026. Verfasst von Yan-Lin Chen und 2 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Statistics, National Yang Ming Chiao Tung University, Hsinchu 300093, Taiwan. Hauptthemen laut MEDLINE: Mediation Analysis. Die Arbeit nennt 22 Literaturangaben. Gefördert von: National Science and Technology Council of Taiwan.
Abstract (Originalsprache)
Understanding how an exposure influences an outcome through mediators is essential in medical and epidemiological research, especially when mediators vary over time and influence each other reciprocally. This complex condition, termed causally ordered multiple time-varying mediation, frequently appears in chronic diseases. For instance, in chronic obstructive pulmonary disease, low lung capacity initiates a vicious cycle where dyspnea and physical inactivity reinforce each other, progressively worsening patients’ quality of life. However, existing mediation methods often focus on single time-varying mediators or fail to fully decompose the total effect (TE), making them inadequate for capturing such feedback dynamics. To address these limitations, we propose a novel framework that decomposes the TE into path-specific effects (PSEs) for each mediator, offering a precise and clinically relevant analysis. Our approach ensures that the sum of these PSEs equals the TE, resolving interpretative issues in prior methods. For estimation, we derive efficient influence function and employ targeted maximum likelihood estimation, which combines flexibility with strong statistical properties, including multiple robustness, asymptotic normality, and efficiency. Our framework offers powerful solutions for analyzing complex mediation mechanisms in longitudinal data, with substantial applications in clinical research.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Institute of Statistics, National Yang Ming Chiao Tung University, Hsinchu 300093, Taiwan.
- Institute of Data Science and Engineering, National Yang Ming Chiao Tung University, Hsinchu 300093, Taiwan.
- Department of Applied Mathematics, National Dong Hwa University, Hualien 974301, Taiwan.
- Department of Biochemical and Molecular Medical Sciences, National Dong Hwa University, Hualien 974301, Taiwan.
ORCID-Profile: Yan-Lin Chen, Yun-Hao Chang, Sheng-Hsuan Lin
Förderung
- National Science and Technology Council of Taiwan
Zitieren
APA
Chen, Y. L., Chang, Y. H., & Lin, S. H. (2026). Targeted maximum likelihood estimation for mediation analysis with multiple time-varying mediators. Biometrics, 82(2). https://doi.org/10.1093/biomtc/ujag102
Vancouver
Chen YL, Chang YH, Lin SH. Targeted maximum likelihood estimation for mediation analysis with multiple time-varying mediators. Biometrics. 2026;82(2). doi:10.1093/biomtc/ujag102
BibTeX
@article{Chen2026,
author = {Chen, Yan-Lin and Chang, Yun-Hao and Lin, Sheng-Hsuan},
title = {Targeted maximum likelihood estimation for mediation analysis with multiple time-varying mediators},
journal = {Biometrics},
year = {2026},
volume = {82},
number = {2},
doi = {10.1093/biomtc/ujag102}
}
EUVIMED