{"title":"Bayesian Inference of Dynamic Mediation Models for Longitudinal Data","authors":"Saijun Zhao, Zhiyong Zhang, Hong Zhang","doi":"10.1080/10705511.2023.2230519","DOIUrl":null,"url":null,"abstract":"<p><b>Abstract</b></p><p>Mediation analysis is widely applied in various fields of science, such as psychology, epidemiology, and sociology. In practice, many psychological and behavioral phenomena are dynamic, and the corresponding mediation effects are expected to change over time. However, most existing mediation methods assume a static mediation effect over time, which overlooks the dynamic nature of mediation effect. To address this issue, we propose dynamic mediation models that can capture the dynamic nature of the mediation effect. Specifically, we model the path parameters of mediation models as auto-regressive (AR) processes of time that can vary over time. Additionally, we define the mediation effect under the potential outcome framework, and examine its identification and causal interpretation. Bayesian methods utilizing Gibbs sampling are adopted to estimate unknown parameters in the proposed dynamic mediation models. We further evaluate our proposed models and methods through extensive simulations and illustrate their application through a real data application.</p>","PeriodicalId":21964,"journal":{"name":"Structural Equation Modeling: A Multidisciplinary Journal","volume":"87 3","pages":""},"PeriodicalIF":2.5000,"publicationDate":"2023-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Structural Equation Modeling: A Multidisciplinary Journal","FirstCategoryId":"102","ListUrlMain":"https://doi.org/10.1080/10705511.2023.2230519","RegionNum":2,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MATHEMATICS, INTERDISCIPLINARY APPLICATIONS","Score":null,"Total":0}
引用次数: 0
Abstract
Mediation analysis is widely applied in various fields of science, such as psychology, epidemiology, and sociology. In practice, many psychological and behavioral phenomena are dynamic, and the corresponding mediation effects are expected to change over time. However, most existing mediation methods assume a static mediation effect over time, which overlooks the dynamic nature of mediation effect. To address this issue, we propose dynamic mediation models that can capture the dynamic nature of the mediation effect. Specifically, we model the path parameters of mediation models as auto-regressive (AR) processes of time that can vary over time. Additionally, we define the mediation effect under the potential outcome framework, and examine its identification and causal interpretation. Bayesian methods utilizing Gibbs sampling are adopted to estimate unknown parameters in the proposed dynamic mediation models. We further evaluate our proposed models and methods through extensive simulations and illustrate their application through a real data application.
期刊介绍：
Structural Equation Modeling: A Multidisciplinary Journal publishes refereed scholarly work from all academic disciplines interested in structural equation modeling. These disciplines include, but are not limited to, psychology, medicine, sociology, education, political science, economics, management, and business/marketing. Theoretical articles address new developments; applied articles deal with innovative structural equation modeling applications; the Teacher’s Corner provides instructional modules on aspects of structural equation modeling; book and software reviews examine new modeling information and techniques; and advertising alerts readers to new products. Comments on technical or substantive issues addressed in articles or reviews published in the journal are encouraged; comments are reviewed, and authors of the original works are invited to respond.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
