摘要
目前中介效应检验主要是基于截面数据,但许多时候截面数据的中介分析不适合进行因果推断,因而需要收集历时性的纵向数据,进行纵向数据的中介分析。评介了基于交叉滞后面板模型、多水平模型和潜变量增长模型的纵向数据的中介分析方法及其四个发展。第一,中介效应随时间变化,如连续时间模型、多层时变系数模型。第二,中介效应随个体变化,如随机效应的交叉滞后面板模型和多层自回归中介模型。第三,中介模型的整合,如交叉滞后面板模型与多水平模型整合为多层自回归中介模型。第四,中介检验方法的发展,建议使用Bootstrap和贝叶斯法进行纵向数据的中介分析。总结出一个纵向数据的中介分析流程并给出相应的Mplus程序。随后展望了纵向数据的中介分析的拓展方向。
Over the past 30 years, most efforts on testing for mediation have been based on cross-sectional data, which may not get causal inference. A possible solution for this could be to collect longitudinal data and perform a longitudinal mediation analysis. There are three causal arrows in a simple mediation model for analyzing a system of causality. If there is at least one causal arrow where the effect arises sometime after the cause, a longitudinal mediation design will be necessary for effectively observing the causation. There are three types of longitudinal mediation analysis approaches:(1) cross-lagged panel model(CLPM);(2) multilevel mediation model(MLM);(3) latent growth mediation model(LGM). There are four types of development of longitudinal mediation analysis. First, time-varying effect of mediation effect is tested. Continuous time models(CTM) would illustrate how mediating effects vary as a function of lag. Multilevel time-varying coefficient model(MTVCM) can capture direct and indirect effects over time. Second, individuals-varying effect of mediation effect is investigated. Random-effects cross-lagged panel model(RE-CLPM) and Multilevel autoregressive mediation model(MAMM) should be adopted to analyze longitudinal mediation. Third, during integration between different longitudinal mediation models, the outstanding performance is the integration of CLPM and MLM into MAMM. Fourth, the method testing mediation analysis is compared. Bayesian method should be adopted in mediation analysis of MAMM and MTVCM. Bootstrap method should be adopted in mediation analysis of LGM. In the present study, we propose a procedure to analyze longitudinal mediation analysis. The first step is to decide whether it is necessary to make a causal inference. If the aim of research is to make a causal inference, then proceed with the second step. Otherwise, LGM or MLM should be adopted to analyze longitudinal mediation. In the second step, we decide whether it is necessary to test time-varying effect of mediation effect. If the aim of research is to test the time-varying effect of mediation effect, CTM should be adopted to analyze longitudinal mediation. Otherwise, proceed with the third step. The third step is to decide whether it is necessary to investigate the individuals-varying effect of mediation effect. If the aim of research is to investigate the individuals-varying effect of mediation effect, RE-CLPM model or MAMM should be adopted to analyze longitudinal mediation. Otherwise, CLPM should be adopted to analyze longitudinal mediation.
作者
方杰
温忠麟
邱皓政
Fang Jie;Wen Zhonglin;Chiou Hawjeng(Department of Applied Psychology,Guangdong University of Finance&Economics,Guangzhou,510320;Center for Studies of Psychological Application&School of Psychology,South China Normal University,Guangzhou,510631;College of Management,Taiwan Normal University,Taibei)
出处
《心理科学》
CSSCI
CSCD
北大核心
2021年第4期989-996,共8页
Journal of Psychological Science
基金
国家自然科学基金项目(31771245)
国家社会科学基金项目(17BTJ035)的资助。
