关于二分类中介变量非差异错误分类偏倚的分析结果。
Analytic results on the bias due to nondifferential misclassification of a binary mediator.
机构信息
Program on Causal Inference, Department of Epidemiology, Harvard School of Public Health, Boston, Massachusetts 02116, USA.
出版信息
Am J Epidemiol. 2012 Sep 15;176(6):555-61. doi: 10.1093/aje/kws131. Epub 2012 Aug 28.
Abstract
Consider a study in which the effect of a binary exposure on an outcome operates partly through a binary mediator but measurement of the mediator is nondifferentially misclassified. Suppose that an investigator wishes to estimate the direct and indirect effects of the exposure on the outcome. In this paper, the authors describe a mathematical correspondence between the empirical expressions for the natural direct effect and the effect of exposure among the unexposed standardized by a binary confounder. They then exploit this correspondence to prove that the direction of the bias due to nondifferential measurement error in estimating the natural direct and indirect effects is to overestimate the natural direct effect and underestimate the natural indirect effect.
摘要
考虑一项研究，其中二元暴露对结果的影响部分通过二元中介起作用，但中介的测量存在非差异错误分类。假设研究人员希望估计暴露对结果的直接和间接影响。在本文中，作者描述了经验表达式之间的数学对应关系自然直接效应和暴露在未暴露的暴露之间的效应标准化通过二元混杂因素。然后，他们利用这种对应关系证明了由于自然直接和间接效应估计中的非差异测量误差而导致的偏差的方向是高估自然直接效应和低估自然间接效应。
相似文献
1
Analytic results on the bias due to nondifferential misclassification of a binary mediator.关于二分类中介变量非差异错误分类偏倚的分析结果。
Am J Epidemiol. 2012 Sep 15;176(6):555-61. doi: 10.1093/aje/kws131. Epub 2012 Aug 28.
2
On the nondifferential misclassification of a binary confounder.关于二元混杂因素的非差异错误分类。
Epidemiology. 2012 May;23(3):433-9. doi: 10.1097/EDE.0b013e31824d1f63.
3
Effect decomposition in the presence of an exposure-induced mediator-outcome confounder.存在暴露引起的中介结局混杂因素时的效应分解。
Epidemiology. 2014 Mar;25(2):300-6. doi: 10.1097/EDE.0000000000000034.
4
Identification of natural direct effects when a confounder of the mediator is directly affected by exposure.当一个混杂因素的中间变量受到暴露的直接影响时，识别自然直接效应。
Epidemiology. 2014 Mar;25(2):282-91. doi: 10.1097/EDE.0000000000000054.
5
Results on differential and dependent measurement error of the exposure and the outcome using signed directed acyclic graphs.使用有向无环图（DAG）对暴露和结局的差异和相关测量误差进行分析。
Am J Epidemiol. 2012 Jun 15;175(12):1303-10. doi: 10.1093/aje/kwr458. Epub 2012 May 8.
6
Mediation analysis with multiple versions of the mediator.中介分析与多个版本的中介。
Epidemiology. 2012 May;23(3):454-63. doi: 10.1097/EDE.0b013e31824d5fe7.
7
Misclassification of the mediator matters when estimating indirect effects.当估计间接效应时，调解者的错误分类很重要。
J Epidemiol Community Health. 2013 May;67(5):458-66. doi: 10.1136/jech-2012-201813. Epub 2013 Mar 16.
8
A principal stratification approach for evaluating natural direct and indirect effects in the presence of treatment-induced intermediate confounding.一种用于在存在治疗诱导的中间混杂因素的情况下评估自然直接效应和间接效应的主分层方法。
Stat Med. 2015 Jan 15;34(1):131-44. doi: 10.1002/sim.6329. Epub 2014 Oct 14.
9
Differential misclassification arising from nondifferential errors in exposure measurement.暴露测量中非差异误差引起的差异错分。
Am J Epidemiol. 1991 Nov 15;134(10):1233-44. doi: 10.1093/oxfordjournals.aje.a116026.
10
Bias Formulas for Estimating Direct and Indirect Effects When Unmeasured Confounding Is Present.存在未测量混杂因素时估计直接效应和间接效应的偏差公式。
Epidemiology. 2016 Jan;27(1):125-32. doi: 10.1097/EDE.0000000000000407.
引用本文的文献
1
Practical challenges in mediation analysis: a guide for applied researchers.中介分析中的实际挑战：应用研究人员指南
Health Serv Outcomes Res Methodol. 2025;25(1):57-84. doi: 10.1007/s10742-024-00327-4. Epub 2024 Apr 12.
2
Hypertension and Stroke as Mediators of Air Pollution Exposure and Incident Dementia.高血压和中风作为空气污染暴露与新发痴呆的中介因素。
JAMA Netw Open. 2023 Sep 5;6(9):e2333470. doi: 10.1001/jamanetworkopen.2023.33470.
3
Mediation analysis in the presence of continuous exposure measurement error.存在连续暴露测量误差时的中介分析。
Stat Med. 2023 May 20;42(11):1669-1686. doi: 10.1002/sim.9693. Epub 2023 Mar 4.
4
Do peer social relationships mediate the harmful effects of a housing mobility experiment on boys' risky behaviors?同伴社会关系是否在住房流动实验对男孩危险行为的有害影响中起中介作用？
Ann Epidemiol. 2020 Aug;48:36-42.e3. doi: 10.1016/j.annepidem.2020.05.007. Epub 2020 May 27.
5
Efficiency and robustness of causal effect estimators when noncompliance is measured with error.当非依从性的测量存在误差时，因果效应估计的效率和稳健性。
Stat Med. 2018 Dec 10;37(28):4126-4141. doi: 10.1002/sim.7922. Epub 2018 Aug 14.
6
Housing mobility and adolescent mental health: The role of substance use, social networks, and family mental health in the Moving to Opportunity Study.住房流动性与青少年心理健康：在“搬到机会”研究中物质使用、社交网络和家庭心理健康的作用。
SSM Popul Health. 2017 Dec;3:318-325. doi: 10.1016/j.ssmph.2017.03.004. Epub 2017 Mar 18.
7
Estimating causal effects from a randomized clinical trial when noncompliance is measured with error.在测量不依从存在误差的情况下，从随机临床试验估计因果效应。
Biostatistics. 2018 Jan 1;19(1):103-118. doi: 10.1093/biostatistics/kxx029.
8
Mediators of First- Versus Second-generation Antipsychotic-related Mortality in Older Adults.老年人中第一代与第二代抗精神病药物相关死亡率的介导因素
Epidemiology. 2015 Sep;26(5):700-9. doi: 10.1097/EDE.0000000000000321.
9
The explanatory role of stroke as a mediator of the mortality risk difference between older adults who initiate first- versus second-generation antipsychotic drugs.中风作为第一代与第二代抗精神病药物起始使用者中老年人死亡率风险差异的中介因素的解释作用。
Am J Epidemiol. 2014 Oct 15;180(8):847-52. doi: 10.1093/aje/kwu210. Epub 2014 Sep 18.
10
Quantifying the role of adverse events in the mortality difference between first and second-generation antipsychotics in older adults: systematic review and meta-synthesis.量化不良事件在老年人第一代和第二代抗精神病药物死亡率差异中的作用：系统评价与综合分析
PLoS One. 2014 Aug 20;9(8):e105376. doi: 10.1371/journal.pone.0105376. eCollection 2014.
本文引用的文献
1
On the nondifferential misclassification of a binary confounder.关于二元混杂因素的非差异错误分类。
Epidemiology. 2012 May;23(3):433-9. doi: 10.1097/EDE.0b013e31824d1f63.
2
Odds ratios for mediation analysis for a dichotomous outcome.二分类结局中介分析的优势比。
Am J Epidemiol. 2010 Dec 15;172(12):1339-48. doi: 10.1093/aje/kwq332. Epub 2010 Oct 29.
3
Mediation and moderation of treatment effects in randomised controlled trials of complex interventions.随机对照试验中复杂干预措施治疗效果的中介和调节作用。
Stat Methods Med Res. 2010 Jun;19(3):237-70. doi: 10.1177/0962280209105014. Epub 2009 Jul 16.
4
Marginal structural models for the estimation of direct and indirect effects.用于估计直接效应和间接效应的边际结构模型。
Epidemiology. 2009 Jan;20(1):18-26. doi: 10.1097/EDE.0b013e31818f69ce.
5
Causal directed acyclic graphs and the direction of unmeasured confounding bias.因果有向无环图与未测量混杂偏倚的方向
Epidemiology. 2008 Sep;19(5):720-8. doi: 10.1097/EDE.0b013e3181810e29.
6
The sign of the bias of unmeasured confounding.未测量混杂因素的偏倚迹象。
Biometrics. 2008 Sep;64(3):702-706. doi: 10.1111/j.1541-0420.2007.00957.x. Epub 2007 Dec 31.
7
Reducing suicidal ideation and depressive symptoms in depressed older primary care patients: a randomized controlled trial.降低老年初级保健抑郁症患者的自杀意念和抑郁症状：一项随机对照试验。
JAMA. 2004 Mar 3;291(9):1081-91. doi: 10.1001/jama.291.9.1081.
8
A rating scale for depression.一种抑郁症评定量表。
J Neurol Neurosurg Psychiatry. 1960 Feb;23(1):56-62. doi: 10.1136/jnnp.23.1.56.
9
The effect of misclassification in the presence of covariates.存在协变量时错误分类的影响。
Am J Epidemiol. 1980 Oct;112(4):564-9. doi: 10.1093/oxfordjournals.aje.a113025.
10
The moderator-mediator variable distinction in social psychological research: conceptual, strategic, and statistical considerations.社会心理学研究中的调节变量与中介变量区分：概念、策略及统计考量
J Pers Soc Psychol. 1986 Dec;51(6):1173-82. doi: 10.1037//0022-3514.51.6.1173.
Zotero 插件