基于转变矩阵描述的个体阶段性发展:潜在转变模型  

Describing the Stage Process of Individual through Transition Matrix:Latent Transition Model

作　　者：王碧瑶[1] 张敏强[1] 张洁婷[1] 胡俊[1] 

机构地区：[1]华南师范大学心理学院/心理应用研究中心,广州510631

出　　处：《心理研究》2015年第4期36-43,共8页Psychological Research

摘　　要：纵向研究是心理与社会研究领域的一种重要方法。当研究对象的外显变量和潜在变量都属于类别型数据时,可以用潜在转变模型对数据进行分析。潜在转变模型是一种个体定向的纵向数据分析方法,能够通过转变矩阵估计个体在不同时间点潜在状态的变化,从转变概率的角度研究个体的阶段性发展。本文在系统地介绍了潜在转变模型的原理和优点的基础上,结合青少年冲动行为发展的实例介绍具体的分析方法,展示了该方法对纵向数据分析的适用性。Longitudinal method is one of the central topics in the research of developmental psychology. Latent transition model （LTM） is a person-oriented longitudinal method and is suitable for analyzing data with both dependent and independent variables being categorical variables. Latent transition analysis combines the cross-sectional measurement of unobserved heterogeneous groups of individuals and the description of development in terms of change over time by transition matrix. LTM describes the stage process of individual through transition matrix, which provides a new perspective in the study of development, especially in stage process. This paper presents a systematic introduction to latent transition model as well as its advantages in longitudinal data analysis and illustrates the practical use of latent transition analysis by using an example of the development of impulsive behaviors in adolescents.

关 键 词：纵向数据 阶段性发展 潜在转变模型 转变矩阵 

分 类 号：B842[哲学宗教—基础心理学]