Efficient Likelihood Estimation of Generalized Structural Equation Models with a Mix of Normal and Nonnormal Responses

作     者：Rockwood, Nicholas J. 

作者机构：Loma Linda Univ Loma Linda CA 92350 USA 

出 版 物：《PSYCHOMETRIKA》 (心理测量学)

年 卷 期：2021年第86卷第2期

页      面：642-667页

核心收录：

学科分类：0402[教育学-心理学(可授教育学、理学学位）] 04[教育学] 0701[理学-数学] 

主　　题：structural equation modeling latent variable modeling generalized linear models maximum likelihood estimation 

摘      要：A maximum likelihood estimation routine is presented for a generalized structural equation model that permits a combination of response variables from various distributions (e.g., normal, Poisson, binomial, etc.). The likelihood function does not have a closed-form solution and so must be numerically approximated, which can be computationally demanding for models with several latent variables. However, the dimension of numerical integration can be reduced if one or more of the latent variables do not directly affect any nonnormal endogenous variables. The method is demonstrated using an empirical example, and the full estimation details, including first-order derivatives of the likelihood function, are provided.