ISSN 1671-3710
CN 11-4766/R

心理科学进展 ›› 2018, Vol. 26 ›› Issue (5): 781-788.doi: 10.3724/SP.J.1042.2018.00781

• 研究方法 • 上一篇    下一篇


方杰1;  温忠麟2;  吴艳3   

  1.  (1广东财经大学人文与传播学院, 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广东外语外贸大学应用心理学系, 广州 510420)
  • 收稿日期:2017-08-04 出版日期:2018-05-15 发布日期:2018-03-30
  • 通讯作者: 方杰, E-mail: E-mail:E-mail:
  • 基金资助:
     国家自然科学基金项目(31771245, 31400909)、国家社会科学基金项目(17BTJ035)、教育部人文社会科学研究青年基金项目(14YJC190003)资助。

 The analyses of multilevel moderation effects based on structural equation modeling

 FANG Jie1; WEN Zhonglin2; WU Yan3   

  1.  (1 School of Humanities and Communication, Guangdong University of Finance & Economics, Guangzhou 510320, China) (2 Center for Studies of Psychological Application & School of Psychology, South China Normal University, Guangzhou 510631, China) (3 Department of Applied Psychology, Guangdong University of Foreign Studies, Guangzhou 510420, China)
  • Received:2017-08-04 Online:2018-05-15 Published:2018-03-30
  • Contact: FANG Jie, E-mail: E-mail:E-mail:
  • Supported by:

摘要: 使用多层线性模型进行调节效应分析在社科领域已常有应用。尽管多层线性模型区分了层1自变量的组间和组内效应、实现了多层调节效应的分解, 仍然存在抽样误差和测量误差。建议在多层结构方程模型框架下, 设置潜变量和多指标来有效校正抽样误差和测量误差。在介绍多层调节SEM分析的随机系数预测法和潜调节结构方程法后, 总结出一套多层调节的SEM分析流程, 通过一个例子来演示如何用Mplus软件进行多层调节SEM分析。随后评述了多层调节效应分析方法在国内心理学的应用现状, 并展望了多层结构方程和多层调节研究的拓展方向。

关键词: 多层线性模型, 调节效应, 抽样误差, 随机系数, 潜调节结构方程

Abstract:  In recent years, multilevel models (MLM) have been frequently used for studying multilevel moderation in social sciences. However, there still exist sampling errors and measurement errors even after separating the between-group effects from the within-group effects of multilevel moderation. To solve this problem, a new method has been developed abroad by integrating MLM with structural equation models (SEM) under the framework of multilevel structural equation models (MSEM) to set latent variables and multiple indicators. It has been showed that the method could rectify sampling errors and measurement errors effectively and obtain more accurate estimation of moderating effects. After introducing the new method by modeling with random coefficient prediction and with latent moderated structural equations, we propose a procedure for analyzing multilevel moderation by using MSEM. An example is illustrated with the software Mplus. Totally 29 articles, published in Chinese psychological journals from 2010 to 2017, are reviewed for evaluating the situation of using multilevel moderation analysis methods in psychological researches in China. Directions for future study on multilevel moderation and MSEM were discussed at the end of the paper.

Key words: multilevel model, multilevel moderation, sampling error, random coefficient, Latent moderated structural equation