潜在类别模型的原理、步骤及程序

doi:10.16382/j.cnki.1000-5560.2023.01.001

摘要/Abstract

摘要：

潜在类别分析和潜在剖面分析相应的模型统称为潜在类别模型，它是根据个体在观测指标上的不同反应模式将其进行分类，从而达到识别群体异质性的一类统计方法，在教育学、心理学等社科领域日益受到应用研究者的关注。然而现有的中文文献对此类模型的统计原理和分析步骤的介绍不易为教育研究工作者所接受。本文系统讲述潜在类别模型的基础知识、统计原理、分析步骤和Mplus程序，厘清潜在类别模型的后续分析所涉及的多种方法和选用策略，有助于增进应用研究者对潜在类别模型的原理理解和方法掌握，推动潜在类别模型在教育研究中的应用。

关键词: 潜在类别模型, 潜在类别分析, 潜在剖面分析, 潜在转变分析, 类别概率, 条件概率

Abstract:

The models used in Latent Class Analysis and Latent Profile Analysis are collectively referred to as latent class models, a kind of statistical methods of classifying individuals according to their different response patterns in observation indicators, so as to identify population heterogeneity. It has attracted increasing attention from applied researchers in the fields of pedagogy, psychology, and other social science disciplines. However, it is not easy for most education researchers to understand the existing Chinese literature on the statistical principles and analytical procedures of such models. This paper systematically introduces the basic knowledge, statistical principles, analytical procedures and Mplus programs of latent class models, and clarifies various methods and selection strategies involved in the subsequent analysis of these models. It would help applied researchers enhance their understanding of the principles and methods of the latent class models, and promote the application of these models to educational research.

Key words: latent class model, Latent Class Analysis, Latent Profile Analysis, Latent Transition Analysis, category probability, conditional probability

温忠麟, 谢晋艳, 王惠惠. 潜在类别模型的原理、步骤及程序[J]. 华东师范大学学报(教育科学版), 2023, 41(1): 1-15.

Zhonglin Wen, Jinyan Xie, Huihui Wang. Principles, Procedures and Programs of Latent Class Models[J]. Journal of East China Normal University(Educational Sciences), 2023, 41(1): 1-15.

图/表 2

参考文献 0

	陈宇帅, 温忠麟, 顾红磊. (2015). 因子混合模型: 潜在类别分析与因子分析的整合. 心理科学进展, 23 (3), 529- 538.
	何妍, 袁柯曼, 张明明, 边玉芳. (2023). 父母控制亚型及其对青少年适应的影响. 华东师范大学学报(教育科学版), 41 (1), 25- 39.
	黄菲菲, 张敏强, 崔雪平, 黄熙彤, 甘露. (2018). 家校关系类型对小学生学业成绩的影响: 基于潜在剖面分析. 教育研究与实验, (2), 88- 91.
	黄声华, 尹弘飚, 靳玉乐. (2023). 家长教育卷入类型特征及其与中学生学科素养的关系: 基于PISA 2018中国香港及澳门数据的潜在类别分析. 华东师范大学学报(教育科学版), 41 (1), 50- 59.
	廖友国, 王峥, 陈建文, 张妍, 张本钰. (2021). 初中生外化问题行为的潜在类别及其影响因素. 中国临床心理学杂志, 29 (2), 297- 300+305.
	刘红云. (2019). 高级心理统计. 北京: 中国人民大学出版社.
	邱皓政. (2008). 潜在类别模型的原理与技术. 北京: 教育科学出版社.
	孙思雨, 许添舒, 孔企平. (2022). 基于潜在类别分析的小学生早期代数思维水平研究. 数学教育学报, 31 (1), 52- 58.
	王碧瑶, 张敏强, 张洁婷, 胡俊. (2015). 基于转变矩阵描述的个体阶段性发展: 潜在转变模型. 心理研究, 8 (4), 36- 43. doi: 10.3969/j.issn.2095-1159.2015.04.006
	王孟成, 毕向阳. (2018a). 回归混合模型: 方法进展与软件实现. 心理科学进展, 26 (12), 2272- 2280.
	王孟成, 毕向阳. (2018b). 潜变量建模与Mplus应用•进阶篇. 重庆: 重庆大学出版社.
	王孟成, 邓俏文, 毕向阳, 叶浩生, 杨文登. (2017). 分类精确性指数Entropy在潜剖面分析中的表现: 一项蒙特卡罗模拟研究. 心理学报, 49 (11), 1473- 1482.
	温聪聪, 朱红. (2021). 随机截距潜在转变分析(RI-LTA)——个案自我转变与个案间差异的分离. 心理科学进展, 29 (10), 1773- 1782.
	温忠麟. (2016). 心理与教育统计(第二版). 广州: 广东高等教育出版社.
	温忠麟, 方杰, 陈虹熹, 叶宝娟, 蔡保贞. (2022). 新世纪20年国内测验信度研究. 心理科学进展, 30 (8), 1682- 1691.
	吴旻, 宋文琦, 梁丽婵. (2023). 农村小学生同伴攻击−受侵害类型及其学校适应: 基于潜在剖面分析. 华东师范大学学报(教育科学版), 41 (1), 40- 49.
	尹奎, 彭坚, 张君. (2020). 潜在剖面分析在组织行为领域中的应用. 心理科学进展, 28 (7), 1056- 1070.
	臧蓓蕾, 张俊. (2017). 基于潜在类别分析的方法探究3~5岁儿童心理数线发展的特点. 学前教育研究, (7), 49- 60.
	张洁婷, 焦璨, 张敏强. (2010). 潜在类别分析技术在心理学研究中的应用. 心理科学进展, 18 (12), 1991- 1998.
	张文明, 陈嘉晟. (2022). 中小学生肥胖问题研究: 校际差异及时间分配表征. 华东师范大学学报(教育科学版), 40 (2), 43- 56.
	赵雪艳, 游旭群, 秦伟. (2023). 中学教师情绪劳动策略与职业幸福感指标的关系: 基于潜在剖面分析. 华东师范大学学报(教育科学版), 41 (1), 16- 24.
	Asparouhov, T. & Muthén, B. O. (2014). Auxiliary variables in mixture modeling: Three-step approaches using Mplus. Structural Equation Modeling:A Multidisciplinary Journal, 21 (3), 329- 341. doi: 10.1080/10705511.2014.915181
	Asparouhov, T. , & Muthen, B. (2021). Auxiliary Variables in Mixture Modeling: Using the BCH method in Mplus to estimate a distal outcome model and an arbitrary secondary model. Mplus Web Notes: No. 21. Los Angeles, CA: Muthén & Muthén.
	Bakk, Z., Oberski, D. L., & Vermunt, J. K. (2016). Relating latent class membership to continuous distal outcomes: Improving the LTB approach and a modified three-step implementation. Structural Equation Modeling:A Multidisciplinary Journal, 23 (2), 278- 289. doi: 10.1080/10705511.2015.1049698
	Bakk, Z, & Vermunt, J. K. (2016). Robustness of stepwise latent class modeling with continuous distal outcomes. Structural Equation Modeling:A Multidisciplinary Journal, 23 (1), 20- 31. doi: 10.1080/10705511.2014.955104
	Bandeen-Roche, K., Miglioretti, D. L., Zeger, S. L., & Rathouz, P. R. (1997). Latent variable regression for multiple discrete outcomes. Journal of the American Statistical Association, 92 (440), 1375- 1386. doi: 10.1080/01621459.1997.10473658
	Bolck, A., Croon, M., & Hagenaars, J. (2004). Estimating latent structure models with categorical variables: One-step versus three-step estimators. Political Analysis, 12 (1), 3- 27. doi: 10.1093/pan/mph001
	Clark, S. L. , & Muthén, B. O. (2009). Relating latent class analysis results to variables not included in the analysis. Retrieved from https://www.statmodel.com/download/relatinglca.pdf.
	Collins, L. M. , & Lanza, S. T. (2010). Latent Class and Latent Transition Analysis: With Applications in the Social, Behavioral, and Health Sciences. Hoboken: John Wiley & Sons.
	Gibson, W. A. (1959). Three multivariate models: Factor analysis, latent structure analysis, and latent profile analysis. Psychometrika, 24 (3), 229- 252. doi: 10.1007/BF02289845
	Hagenaars, J. A. , & McCutcheon, A. L. (2002). Applied Latent Class Analysis. United Kingdom: Cambridge University Press.
	Huang, G. H., Wang, S. M., & Hsu, C. C. (2011). Optimization-based model fitting for latent class and latent profile analyses. Psychometrika, 76 (4), 584- 611. doi: 10.1007/s11336-011-9227-3
	Jung, T., & Wickrama, K. A. (2008). An introduction to latent class growth analysis and growth mixture modeling. Social and Personality Psychology Compass, 2 (1), 302- 317. doi: 10.1111/j.1751-9004.2007.00054.x
	Lanza, S. T., Tan, X., & Bray, B. C. (2013). Latent class analysis with distal outcomes: A flexible model-based approach. Structural Equation Modeling:A Multidisciplinary Journal, 20 (1), 1- 26. doi: 10.1080/10705511.2013.742377
	Lazarsfeld, P. F., & Henry, N. W. (1968). Latent Structure Analysis. Boston, MA: Houghton Mifflin.
	Lubke, G., & Muthén, B. O. (2007). Performance of factor mixture models as a function of model size, covariate effects, and class-specific parameters. Structural Equation Modeling:A Multidisciplinary Journal, 14 (1), 26- 47. doi: 10.1080/10705510709336735
	McLachlan, G. J.. (1987). On bootstrapping the likelihood ratio test statistic for the number of components in a normal mixture model. Journal of the Royal Statistical Society, Series C, Applied Statistics, 36 (4), 318- 324.
	Muthén, B. O, & Asparouhov, T. (2022). Latent transition analysis with random intercepts (RI-LTA). Psychological Methods, 27 (1), 1- 16. doi: 10.1037/met0000370
	Muthén, B. O, & Muthén, L. K. (2000). Integrating person-centered and variable-centered analyses: Growth mixture modeling with latent trajectory classes. Alcoholism:Clinical and Experimental Research, 24 (6), 882- 891. doi: 10.1111/j.1530-0277.2000.tb02070.x
	Muthén, L. K. , & Muthén, B. O. (1998−2022). Mplus User's Guide. Los Angeles, CA: Muthén & Muthén.
	Nylund, K. L., Asparouhov, T., & Muthén, B. O. (2007). Deciding on the number of classes in latent class analysis and growth mixture modeling: A monte carlo simulation study. Structural Equation Modeling:A Multidisciplinary Journal, 14 (4), 535- 569. doi: 10.1080/10705510701575396
	Tein, J. Y., Coxe, S., & Cham, H. (2013). Statistical power to detect the correct number of classes in latent profile analysis. Structural Equation Modeling:A Multidisciplinary Journal, 20 (4), 640- 657. doi: 10.1080/10705511.2013.824781
	Vermunt, J. K. (2010). Latent class modeling with covariates: Two improved three-step approaches. Political Analysis, 18 (4), 450- 469. doi: 10.1093/pan/mpq025

题目1（X₁）	题目2（X₂）			合计	题目1（X₁）	题目2（X₂）			合计
题目1（X₁）	0	1	2	合计	题目1（X₁）	0	1	2	合计
0	20	14	8	42	0	0.10	0.07	0.04	0.21
1	16	32	12	60	1	0.08	0.16	0.06	0.30
2	10	20	24	54	2	0.05	0.10	0.12	0.27
3	6	16	22	44	3	0.03	0.08	0.11	0.22
合计	52	82	66	200	合计	0.26	0.41	0.33	1.00

LCA分类	潜在类别			潜在类别	LCA分类
LCA分类	1	2	3	潜在类别	1	2	3
1	0.875	0.000	0.125	1	0.813	0.000	0.187
2	0.000	0.961	0.039	2	0.000	0.978	0.022
3	0.096	0.021	0.883	3	0.060	0.038	0.901

[1]	黄声华, 尹弘飚, 靳玉乐. 家长教育卷入类型与中学生学科素养：基于PISA 2018中国香港及澳门数据的潜在类别分析[J]. 华东师范大学学报(教育科学版), 2023, 41(1): 50-59.
[2]	吴旻, 宋文琦, 梁丽婵. 农村小学生同伴攻击受侵害类型及其学校适应：基于潜在剖面分析[J]. 华东师范大学学报(教育科学版), 2023, 41(1): 40-49.
[3]	何妍, 袁柯曼, 张明明, 边玉芳. 父母控制亚型及其对青少年适应的影响：基于潜在转变分析[J]. 华东师范大学学报(教育科学版), 2023, 41(1): 25-39.
[4]	赵雪艳, 游旭群, 秦伟. 中学教师情绪劳动策略与职业幸福感的关系：基于潜在剖面分析[J]. 华东师范大学学报(教育科学版), 2023, 41(1): 16-24.
[5]	余达祥. 条件推理概率解释模型中的隐性预设及其实证检验[J]. 华东师范大学学报(教育科学版), 2009, 27(3): 46-54.