检验中介效应和其他干预变量效应的方法比较。
A comparison of methods to test mediation and other intervening variable effects.
作者信息
MacKinnon David P, Lockwood Chondra M, Hoffman Jeanne M, West Stephen G, Sheets Virgil
机构信息
Department of Psychology, Arizona State University, Tempe 85287-1104, USA.
出版信息
Psychol Methods. 2002 Mar;7(1):83-104. doi: 10.1037/1082-989x.7.1.83.
Abstract
A Monte Carlo study compared 14 methods to test the statistical significance of the intervening variable effect. An intervening variable (mediator) transmits the effect of an independent variable to a dependent variable. The commonly used R. M. Baron and D. A. Kenny (1986) approach has low statistical power. Two methods based on the distribution of the product and 2 difference-in-coefficients methods have the most accurate Type I error rates and greatest statistical power except in 1 important case in which Type I error rates are too high. The best balance of Type I error and statistical power across all cases is the test of the joint significance of the two effects comprising the intervening variable effect.
摘要
一项蒙特卡洛研究比较了14种方法，以检验中介变量效应的统计显著性。中介变量将自变量的效应传递给因变量。常用的R.M.巴伦和D.A.肯尼（1986年）方法的统计功效较低。除了在一种重要情况下I型错误率过高外，基于乘积分布的两种方法和两种系数差异方法具有最准确的I型错误率和最大的统计功效。在所有情况下，I型错误和统计功效的最佳平衡是对构成中介变量效应的两种效应的联合显著性检验。
相似文献
1
A comparison of methods to test mediation and other intervening variable effects.检验中介效应和其他干预变量效应的方法比较。
Psychol Methods. 2002 Mar;7(1):83-104. doi: 10.1037/1082-989x.7.1.83.
2
Testing mediation in nursing research: beyond Baron and Kenny.护理研究中的中介效应检验：超越 Baron 和 Kenny。
Nurs Res. 2010 Jul-Aug;59(4):288-94. doi: 10.1097/NNR.0b013e3181dd26b3.
3
Assessing Mediational Models: Testing and Interval Estimation for Indirect Effects.评估中介模型：间接效应的检验与区间估计
Multivariate Behav Res. 2010 Aug 6;45(4):661-701. doi: 10.1080/00273171.2010.498292.
4
Mediation in experimental and nonexperimental studies: new procedures and recommendations.实验性研究与非实验性研究中的中介作用：新程序与建议
Psychol Methods. 2002 Dec;7(4):422-45.
5
Evaluating and rejecting true mediation models: a cautionary note.评估并拒绝真实的中介模型：一则警示
Prev Sci. 2002 Dec;3(4):285-9. doi: 10.1023/a:1020828709115.
6
Monte Carlo based statistical power analysis for mediation models: methods and software.基于蒙特卡洛方法的中介模型统计功效分析：方法与软件
Behav Res Methods. 2014 Dec;46(4):1184-98. doi: 10.3758/s13428-013-0424-0.
7
A Statistical Method for Synthesizing Mediation Analyses Using the Product of Coefficient Approach Across Multiple Trials.一种使用跨多个试验的系数乘积法综合中介分析的统计方法。
Stat Methods Appt. 2016 Nov;25(4):565-579. doi: 10.1007/s10260-016-0354-y. Epub 2016 Feb 25.
8
A Simple Configural Approach for Testing Person-Oriented Mediation Hypotheses.一种用于检验以人为主的中介假设的简单结构方法。
Integr Psychol Behav Sci. 2021 Sep;55(3):637-664. doi: 10.1007/s12124-020-09598-1. Epub 2021 Feb 25.
9
Two-condition within-participant statistical mediation analysis: A path-analytic framework.两条件组内被试统计中介分析：路径分析框架。
Psychol Methods. 2017 Mar;22(1):6-27. doi: 10.1037/met0000086. Epub 2016 Jun 30.
10
Mediation analysis with binary outcomes: Direct and indirect effects of pro-alcohol influences on alcohol use disorders.中介分析与二元结局：促进酒精影响对酒精使用障碍的直接和间接作用。
Addict Behav. 2019 Jul;94:26-35. doi: 10.1016/j.addbeh.2018.12.018. Epub 2018 Dec 15.
引用本文的文献
1
Determining the power of a 1-sided z-test given only the power of the corresponding 2-sided test.仅根据相应双侧检验的功效来确定单侧Z检验的功效。
J Behav Med. 2025 Sep 9. doi: 10.1007/s10865-025-00595-6.
2
Causal Relationship Between Serum Uric Acid and Atherosclerotic Disease: A Mendelian Randomization and Transcriptomic Analysis.血清尿酸与动脉粥样硬化性疾病之间的因果关系：孟德尔随机化和转录组分析
Biomedicines. 2025 Jul 28;13(8):1838. doi: 10.3390/biomedicines13081838.
3
The Impact of School Burnout on Life Satisfaction Among University Students: The Mediating Effects of Loneliness and Fear of Alienation.学校倦怠对大学生生活满意度的影响：孤独感和对被疏远的恐惧的中介作用。
Behav Sci (Basel). 2025 Aug 9;15(8):1083. doi: 10.3390/bs15081083.
4
Hypothesis Tests of Indirect Effects for Multiple Mediators.多个中介变量间接效应的假设检验
Stat Methods Appt. 2025 Mar;34(1):113-127. doi: 10.1007/s10260-024-00777-7. Epub 2025 Jan 16.
5
The parallel mediating role of time and financial resources in achievement motivation and non-credential learning.时间和财务资源在成就动机与非学历学习中的平行中介作用。
Front Psychol. 2025 Aug 4;16:1579281. doi: 10.3389/fpsyg.2025.1579281. eCollection 2025.
6
"Have you considered that it could be burnout?"-psychologization and stigmatization of self-reported long COVID or post-COVID-19 vaccination syndrome.“你是否考虑过这可能是倦怠？”——自我报告的长期新冠或新冠疫苗接种后综合征的心理化与污名化
BMC Med. 2025 Aug 20;23(1):488. doi: 10.1186/s12916-025-04335-0.
7
Associations between muscle mass and strength and bone microarchitecture in Caucasian postmenopausal women.高加索绝经后女性肌肉质量与力量和骨微结构之间的关联。
Osteoporos Int. 2025 Aug 19. doi: 10.1007/s00198-025-07653-4.
8
Blood-brain barrier disruption mediates the association between cerebral small vessel disease and clinical outcome after stroke: a secondary analysis of the Lesion Evolution in Stroke and Ischemia on Neuroimaging study.血脑屏障破坏介导脑小血管病与卒中后临床结局之间的关联：卒中与缺血性神经影像学病变演变研究的二次分析
Front Stroke. 2024;3. doi: 10.3389/fstro.2024.1510359. Epub 2024 Dec 4.
9
Immune cells, inflammatory proteins, and sepsis: A mediation Mendelian randomization study.免疫细胞、炎症蛋白与脓毒症：一项中介孟德尔随机化研究
Medicine (Baltimore). 2025 Aug 8;104(32):e43779. doi: 10.1097/MD.0000000000043779.
10
M-CSF Protects Against Ulcerative Colitis via Aconitate: Mendelian Randomization and Experimental Evidence.巨噬细胞集落刺激因子通过乌头酸预防溃疡性结肠炎：孟德尔随机化和实验证据
J Inflamm Res. 2025 Jul 31;18:10313-10329. doi: 10.2147/JIR.S528072. eCollection 2025.
本文引用的文献
1
A Simulation Study of Mediated Effect Measures.中介效应测量的模拟研究
Multivariate Behav Res. 1995 Jan 1;30(1):41. doi: 10.1207/s15327906mbr3001_3.
2
On a distinction between hypothetical constructs and intervening variables.论假设构念与中介变量之间的区别。
Psychol Rev. 1948 Mar;55(2):95-107. doi: 10.1037/h0056029.
3
Equivalence of the mediation, confounding and suppression effect.中介效应、混杂效应和抑制效应的等效性。
Prev Sci. 2000 Dec;1(4):173-81. doi: 10.1023/a:1026595011371.
4
School-based substance abuse prevention: a review of the state of the art in curriculum, 1980-1990.以学校为基础的药物滥用预防：1980 - 1990年课程发展现状综述
Health Educ Res. 1992 Sep;7(3):403-30. doi: 10.1093/her/7.3.403.
5
Analysis of mediating variables in prevention and intervention research.预防与干预研究中的中介变量分析
NIDA Res Monogr. 1994;139:127-53.
6
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.
7
Sample size for studying intermediate endpoints within intervention trails or observational studies.干预试验或观察性研究中用于研究中间终点的样本量。
Am J Epidemiol. 1992 Nov 1;136(9):1148-59. doi: 10.1093/oxfordjournals.aje.a116581.
Zotero 插件