密集追踪数据的中介效应分析  

Mediation analysis of intensive longitudinal data

作　　者：方杰[1] 温忠麟 董育铭 王晓洁 FANG Jie;WEN Zhonglin;DONG Yuming;WANG Xiaojie(Institute of New Development,Guangdong University of Finance&Economics,Guangzhou 510320,China;Center for Studies of Psychological Application&School of Psychology,South China Normal University,Guangzhou 510631,China;The School of Economics,Guangdong University of Finance&Economics,Guangzhou 510320,China)

机构地区：[1]广东财经大学新发展研究院,广州510320 [2]华南师范大学心理学院/心理应用研究中心,广州510631 [3]广东财经大学经济学院,广州510320

出　　处：《心理科学进展》2025年第4期717-728,共12页Advances in Psychological Science

基　　金：国家自然科学基金项目(32171091);教育部人文社会科学研究规划基金项目(24YJA190003);青年基金项目(23YJC190026)资助。

摘　　要：随着密集追踪数据在社科领域的广泛运用,如何对密集追踪数据进行中介效应分析吸引了诸多研究者的注意。如果还是按通常追踪数据一样对待,采用多水平模型和多水平结构方程模型进行中介效应分析,则既忽略了变量之间的先后顺序,也无法探究变量之间动态变化的关联。本文以1-1-1密集追踪中介模型为例,详述了基于多水平自回归模型(MAM)及其变式(残差MAM)、动态结构方程模型(DSEM)及其变式(残差DSEM、交叉分类的DSEM)的密集追踪中介效应分析方法,并总结出一个分析流程。用示例演示如何进行密集追踪数据的中介效应分析,并给出了相应的Mplus和R程序。最后讨论了密集追踪数据的中介效应分析的拓展方向。With the widespread use of intensive longitudinal data in the social sciences,how to analysis intensive longitudinal mediation(ILM)effect has attracted the attention of many researchers.A conventional approach is using multilevel models or multilevel structural equation models.In that case,the temporal sequence of variables is ignored,with the dynamic relationship between variables remaining unexplored.In this paper,we summarize five types of ILM analysis approaches:1)multilevel autoregressive model(MAM);2)residual multilevel autoregressive model(RMAM);3)dynamic structural equation model(DSEM);4)residual dynamic structural equation model(RDSEM);5)cross-classified dynamic structural equation model(cross-classified DSEM).ILM effects with time changes can only be analyzed by cross-classified DSEM;other models can only obtain ILM effects with individual changes.After introducing the new method,we proposed a procedure for analyzing ILM effects.Then,this paper exemplifies how to conduct the proposed procedure and provides corresponding Mplus and R codes.Directions for future study on mediation analysis of intensive longitudinal data were discussed at the end of the paper.

关 键 词：密集追踪数据 中介效应 多水平自回归模型 动态结构方程模型 去趋势 

分 类 号：B841[哲学宗教—基础心理学]