期刊
AMERICAN JOURNAL OF EPIDEMIOLOGY
卷 190, 期 4, 页码 663-672出版社
OXFORD UNIV PRESS INC
DOI: 10.1093/aje/kwaa225
关键词
complete cases; inverse probability weighting; last observation carried forward; missingness pattern approach; multiple imputation; propensity score; time-varying confounding
资金
- Medical Research Council [MR/M013278/1, MC UU 12023/21, MC UU 12023/29]
- e-Health and Integrated Care Chair of Excellence of the Universite Grenoble Alpes Foundation
- Agence Nationale de la Recherche's Institut Interdisciplinaire d'Intelligence Artificielle MIAI@Grenoble Alpes project (Multidisciplinary Institute of Artificial Intelligence)
- MRC [MR/M013278/1, MR/S01442X/1, MC_UU_12023/21] Funding Source: UKRI
Marginal structural models (MSMs) are commonly used to estimate causal intervention effects in longitudinal nonrandomized studies. Handling missing confounder data in observational studies using MSMs remains a challenge, with limited guidance on practical approaches. Careful consideration of missingness reasons, potential modifications of existing data relationships, and the scientific context is essential for choosing appropriate methods in MSM analysis.
Marginal structural models (MSMs) are commonly used to estimate causal intervention effects in longitudinal nonrandomized studies. A common challenge when using MSMs to analyze observational studies is incomplete confounder data, where a poorly informed analysis method will lead to biased estimates of intervention effects. Despite a number of approaches described in the literature for handling missing data in MSMs, there is little guidance on what works in practice and why. We reviewed existing missing-data methods for MSMs and discussed the plausibility of their underlying assumptions. We also performed realistic simulations to quantify the bias of 5 methods used in practice: complete-case analysis, last observation carried forward, the missingness pattern approach, multiple imputation, and inverse-probability-of-missingness weighting. We considered 3 mechanisms for nonmonotone missing data encountered in research based on electronic health record data. Further illustration of the strengths and limitations of these analysis methods is provided through an application using a cohort of persons with sleep apnea: the research database of the French Observatoire Sommeil de la Federation de Pneumologie. We recommend careful consideration of 1) the reasons for missingness, 2) whether missingness modifies the existing relationships among observed data, and 3) the scientific context and data source, to inform the choice of the appropriate method(s) for handling partially observed confounders in MSMs.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据