Department of Psychology, McGill University, 1205 Dr. Penfield Avenue, Montreal, Quebec, H3A 1B1, Canada,
Behav Res Methods. 2013 Dec;45(4):1036-47. doi: 10.3758/s13428-013-0335-0.
Studies in the social and behavioral sciences often involve categorical data, such as ratings, and define latent constructs underlying the research issues as being discrete. In this article, models with discrete latent variables (MDLV) for the analysis of categorical data are grouped into four families, defined in terms of two dimensions (time and sampling) of the data structure. A MATLAB toolbox (referred to as the "MDLV toolbox") was developed for applying these models in practical studies. For each family of models, model representations and the statistical assumptions underlying the models are discussed. The functions of the toolbox are demonstrated by fitting these models to empirical data from the European Values Study. The purpose of this article is to offer a framework of discrete latent variable models for data analysis, and to develop the MDLV toolbox for use in estimating each model under this framework. With this accessible tool, the application of data modeling with discrete latent variables becomes feasible for a broad range of empirical studies.
社会科学和行为科学的研究经常涉及分类数据，例如评分，并将研究问题背后的潜在结构定义为离散的。在本文中，用于分析分类数据的具有离散潜在变量（MDLV）的模型被分为四组，根据数据结构的两个维度（时间和抽样）进行定义。开发了一个 MATLAB 工具箱（称为“MDLV 工具箱”），用于在实际研究中应用这些模型。对于每个模型族，讨论了模型表示和模型背后的统计假设。通过将这些模型拟合到欧洲价值观研究的实证数据来展示工具箱的功能。本文的目的是为数据分析提供离散潜在变量模型的框架，并开发 MDLV 工具箱，以在该框架下估计每个模型。有了这个易于使用的工具，使用离散潜在变量进行数据建模的应用对于广泛的实证研究变得可行。
