探索逆概率加权和边缘结构模型的细微差别。
Exploring the Subtleties of Inverse Probability Weighting and Marginal Structural Models.
机构信息
From the Department of Epidemiology, University of North Carolina at Chapel Hill, Chapel Hill, NC.
出版信息
Epidemiology. 2018 May;29(3):352-355. doi: 10.1097/EDE.0000000000000813.
Abstract
Since being introduced to epidemiology in 2000, marginal structural models have become a commonly used method for causal inference in a wide range of epidemiologic settings. In this brief report, we aim to explore three subtleties of marginal structural models. First, we distinguish marginal structural models from the inverse probability weighting estimator, and we emphasize that marginal structural models are not only for longitudinal exposures. Second, we explore the meaning of the word "marginal" in "marginal structural model." Finally, we show that the specification of a marginal structural model can have important implications for the interpretation of its parameters. Each of these concepts have important implications for the use and understanding of marginal structural models, and thus providing detailed explanations of them may lead to better practices for the field of epidemiology.
摘要
自 2000 年引入流行病学以来，边缘结构模型已成为广泛的流行病学环境中因果推断的常用方法。在这份简要报告中，我们旨在探讨边缘结构模型的三个细微差别。首先，我们将边缘结构模型与逆概率加权估计器区分开来，并强调边缘结构模型不仅适用于纵向暴露。其次，我们探讨了“边缘结构模型”中“边缘”一词的含义。最后，我们表明边缘结构模型的规范对其参数的解释有重要影响。这些概念中的每一个都对边缘结构模型的使用和理解有重要影响，因此详细解释它们可能会为流行病学领域带来更好的实践。
相似文献
1
Exploring the Subtleties of Inverse Probability Weighting and Marginal Structural Models.探索逆概率加权和边缘结构模型的细微差别。
Epidemiology. 2018 May;29(3):352-355. doi: 10.1097/EDE.0000000000000813.
2
Differences between marginal structural models and conventional models in their exposure effect estimates: a systematic review.边缘结构模型与传统模型在暴露效应估计中的差异：系统评价。
Epidemiology. 2011 Jul;22(4):586-8. doi: 10.1097/EDE.0b013e31821d0507.
3
Understanding Marginal Structural Models for Time-Varying Exposures: Pitfalls and Tips.理解时变暴露的边际结构模型：陷阱与技巧。
J Epidemiol. 2020 Sep 5;30(9):377-389. doi: 10.2188/jea.JE20200226. Epub 2020 Jul 18.
4
Marginal structural models as a tool for standardization.边际结构模型作为一种标准化工具。
Epidemiology. 2003 Nov;14(6):680-6. doi: 10.1097/01.EDE.0000081989.82616.7d.
5
Structural equation modeling versus marginal structural modeling for assessing mediation in the presence of posttreatment confounding.在存在治疗后混杂因素的情况下，用于评估中介作用的结构方程模型与边际结构模型对比
Psychol Methods. 2015 Jun;20(2):204-20. doi: 10.1037/a0036368. Epub 2015 Mar 9.
6
A cautionary note concerning the use of stabilized weights in marginal structural models.关于在边际结构模型中使用稳定权重的警示说明。
Stat Med. 2015 Feb 28;34(5):812-23. doi: 10.1002/sim.6378. Epub 2014 Nov 19.
7
Marginal structural models and causal inference in epidemiology.边缘结构模型与流行病学中的因果推断
Epidemiology. 2000 Sep;11(5):550-60. doi: 10.1097/00001648-200009000-00011.
8
Marginal Structural Models: unbiased estimation for longitudinal studies.边缘结构模型：纵向研究的无偏估计。
Int J Public Health. 2011 Feb;56(1):117-9. doi: 10.1007/s00038-010-0198-4. Epub 2010 Oct 8.
9
Estimating inverse probability weights using super learner when weight-model specification is unknown in a marginal structural Cox model context.在边际结构Cox模型背景下，当权重模型规范未知时，使用超级学习器估计逆概率权重。
Stat Med. 2017 Jun 15;36(13):2032-2047. doi: 10.1002/sim.7266. Epub 2017 Feb 20.
10
An introduction to g methods.G方法简介。
Int J Epidemiol. 2017 Apr 1;46(2):756-762. doi: 10.1093/ije/dyw323.
引用本文的文献
1
Evaluation of the Effectiveness of Buprenorphine-Naloxone on Opioid Overdose and Death among Insured Patients with Opioid Use Disorder in the United States.丁丙诺啡 - 纳洛酮对美国患有阿片类药物使用障碍的参保患者阿片类药物过量及死亡的有效性评估。
Pharmacoepidemiology. 2022 Dec;1(3):101-112. doi: 10.3390/pharma1030010. Epub 2022 Nov 24.
2
Causal effects of cingulate morphology on executive functions in healthy young adults.扣带回形态对健康年轻成年人执行功能的因果影响。
Hum Brain Mapp. 2022 Oct 1;43(14):4370-4382. doi: 10.1002/hbm.25960. Epub 2022 Jun 6.
3
Contribution of obesity and cardiometabolic risk factors in developing cardiovascular disease: a population-based cohort study.肥胖和心血管代谢危险因素对心血管疾病发展的影响：基于人群的队列研究。
Sci Rep. 2022 Jan 28;12(1):1544. doi: 10.1038/s41598-022-05536-w.
4
Estimating the effects of Mexico to U.S. migration on elevated depressive symptoms: evidence from pooled cross-national cohorts.估计墨西哥向美国移民对抑郁症状升高的影响：来自跨国队列的综合证据。
Ann Epidemiol. 2021 Dec;64:53-66. doi: 10.1016/j.annepidem.2021.08.014. Epub 2021 Aug 23.
5
Metformin use and cirrhotic decompensation in patients with type 2 diabetes and liver cirrhosis.二甲双胍在 2 型糖尿病合并肝硬化患者中的应用与肝硬化失代偿。
Br J Clin Pharmacol. 2022 Jan;88(1):311-322. doi: 10.1111/bcp.14970. Epub 2021 Jul 22.
6
G-computation for policy-relevant effects of interventions on time-to-event outcomes.G 计算在干预措施对时间事件结局的政策相关效应中的应用。
Int J Epidemiol. 2021 Jan 23;49(6):2021-2029. doi: 10.1093/ije/dyaa156.
7
Understanding Marginal Structural Models for Time-Varying Exposures: Pitfalls and Tips.理解时变暴露的边际结构模型：陷阱与技巧。
J Epidemiol. 2020 Sep 5;30(9):377-389. doi: 10.2188/jea.JE20200226. Epub 2020 Jul 18.
8
Marginal structural models for repeated measures where intercept and slope are correlated: An application exploring the benefit of nutritional supplements on weight gain in HIV-infected children initiating antiretroviral therapy.截距与斜率相关的重复测量边际结构模型：一项探索营养补充剂对开始抗逆转录病毒治疗的HIV感染儿童体重增加益处的应用研究
PLoS One. 2020 Jul 9;15(7):e0233877. doi: 10.1371/journal.pone.0233877. eCollection 2020.
9
Comparison of Parametric and Nonparametric Estimators for the Association Between Incident Prepregnancy Obesity and Stillbirth in a Population-Based Cohort Study.基于人群队列研究中，比较参数和非参数估计在偶发性孕前肥胖与死胎之间的关联。
Am J Epidemiol. 2019 Jul 1;188(7):1328-1336. doi: 10.1093/aje/kwz081.
10
Causal criteria: time has come for a revision.因果关系标准：是时候修订了。
Eur J Epidemiol. 2019 Jun;34(6):537-541. doi: 10.1007/s10654-018-00479-x. Epub 2019 Jan 16.
本文引用的文献
1
For and Against Methodologies: Some Perspectives on Recent Causal and Statistical Inference Debates.赞成与反对方法论：对近期因果推断和统计推断争议的一些观点。
Eur J Epidemiol. 2017 Jan;32(1):3-20. doi: 10.1007/s10654-017-0230-6. Epub 2017 Feb 20.
2
Methods for dealing with time-dependent confounding.处理时依混杂的方法。
Stat Med. 2013 Apr 30;32(9):1584-618. doi: 10.1002/sim.5686. Epub 2012 Dec 3.
3
Marginal structural models for case-cohort study designs to estimate the association of antiretroviral therapy initiation with incident AIDS or death.边缘结构模型在病例-队列研究设计中的应用，以估计抗逆转录病毒治疗开始与艾滋病事件或死亡的关联。
Am J Epidemiol. 2012 Mar 1;175(5):381-90. doi: 10.1093/aje/kwr346. Epub 2012 Feb 1.
4
Targeted maximum likelihood estimation of the parameter of a marginal structural model.边际结构模型参数的靶向最大似然估计。
Int J Biostat. 2010;6(2):Article 19. doi: 10.2202/1557-4679.1238. Epub 2010 Apr 15.
5
The relationship between neighborhood poverty and alcohol use: estimation by marginal structural models.邻里贫困与饮酒之间的关系：边际结构模型的估计。
Epidemiology. 2010 Jul;21(4):482-9. doi: 10.1097/EDE.0b013e3181e13539.
6
Time scale and adjusted survival curves for marginal structural cox models.边缘结构 Cox 模型的时间尺度和调整后的生存曲线。
Am J Epidemiol. 2010 Mar 15;171(6):691-700. doi: 10.1093/aje/kwp418. Epub 2010 Feb 5.
7
Observational studies analyzed like randomized experiments: an application to postmenopausal hormone therapy and coronary heart disease.类似随机试验那样分析的观察性研究：绝经后激素治疗与冠心病的应用
Epidemiology. 2008 Nov;19(6):766-79. doi: 10.1097/EDE.0b013e3181875e61.
8
Constructing inverse probability weights for marginal structural models.构建边际结构模型的逆概率权重。
Am J Epidemiol. 2008 Sep 15;168(6):656-64. doi: 10.1093/aje/kwn164. Epub 2008 Aug 5.
9
Assessing the effectiveness of antiretroviral adherence interventions. Using marginal structural models to replicate the findings of randomized controlled trials.评估抗逆转录病毒依从性干预措施的有效性。使用边际结构模型来重现随机对照试验的结果。
J Acquir Immune Defic Syndr. 2006 Dec 1;43 Suppl 1:S96-S103. doi: 10.1097/01.qai.0000248344.95135.8d.
10
Adjusted survival curves with inverse probability weights.采用逆概率加权法调整后的生存曲线。
Comput Methods Programs Biomed. 2004 Jul;75(1):45-9. doi: 10.1016/j.cmpb.2003.10.004.
Zotero 插件