ISSN 1671-3710
CN 11-4766/R

心理科学进展 ›› 2020, Vol. 28 ›› Issue (7): 1056-1070.doi: 10.3724/SP.J.1042.2020.01056

• 研究方法 • 上一篇    下一篇


尹奎1, 彭坚2, 张君3()   

  1. 1北京科技大学东凌经济管理学院, 北京 100083
    2广州大学管理学院, 广州 510006
    3北京石油化工学院人文社科学院, 北京 102617
  • 收稿日期:2018-12-10 出版日期:2020-07-15 发布日期:2020-05-21
  • 通讯作者: 张君
  • 基金资助:
    * 国家自然科学基金项目(71802019);国家自然科学基金项目(71902048);教育部人文社科基金项目(18YJC630230)

The application of latent profile analysis in organizational behavior research

YIN Kui1, PENG Jian2, ZHANG Jun3()   

  1. 1Donlinks School of Economics and Management, University of Science and Technology Beijing, Beijing 100083, China
    2School of Management, Guangzhou University, Guangzhou 510006, China
    3Department of Human Resource Management and Public Administration, Beijing Institute of Petrochemical Technology, Beijing 102617, China
  • Received:2018-12-10 Online:2020-07-15 Published:2020-05-21
  • Contact: Jun ZHANG


以个体为中心的研究路径将各个变量看作是相互依赖的一个系统, 基于多项特征(变量)将被试分为多个子群体, 分析子群体的前因与影响。以个体为中心的研究路径理解更加直观、更贴近实践, 受到越来越多的关注。潜在剖面分析(latent profile analysis, LPA)是以个体为中心研究路径的典型分析技术。在总结归纳以个体与以变量为中心两种研究路径异同、LPA与传统以个体为中心的分析技术差异后, 系统梳理了LPA在组织行为学领域的应用主题, 并从研究主题选取、样本要求、理论使用、剖面数量确定等方面归纳了LPA应用的步骤与注意事项。最后, 提出了未来研究的方向。

关键词: 以个体为中心, 潜在剖面分析, 异质性


A person-centered approach views divergent variables as an interdependent system, and divides the sample into subgroups according to certain participant characteristics to analyze the antecedents and outcomes. This approach has earned much attention because it more closely approximates practice and easier to understand. Latent profile analysis (LPA) is one analytical tool typically used for such analysis. After comparing and contrasting person-centered and variable-centered approaches, and then LPA and similar analysis techniques, we systematically illuminate the domains of the field of organizational behavior where LPA can be applied. We then provide guidance for using LPA as a research method with regard to research theme, sample requirements, the use of theory, and the determination of profile number. Finally, we offer suggestions for the future development of LAP.

Key words: person-centered, latent profile analysis, heterogeneity