Non-linear structural equation models with correlated continuous and discrete data

• Published in: British journal of mathematical & statistical psychology Vol. 62; no. 2; pp. 327 - 347
• Main Authors: Lee, Sik-Yum, Song, Xin-Yuan, Cai, Jing-Heng, So, Wing-Yee, Ma, Ching-Wang, Chan, Chung-Ngor Juliana
• Format: Journal Article
• Language: English
• Published: Oxford, UK Blackwell Publishing Ltd 01.05.2009; British Psychological Society
• Subjects: Algorithms; Alleles; Analysis of Variance; Cardiovascular disease; Cardiovascular Diseases - epidemiology; Cardiovascular Diseases - genetics; Correlation analysis; Data Interpretation, Statistical; Diabetes Mellitus, Type 2 - epidemiology; Diabetes Mellitus, Type 2 - genetics; Estimating techniques; Genetic Markers - genetics; Genetic Predisposition to Disease - genetics; Genotype; Humans; Mathematical models; Maximum likelihood method; Models, Statistical; Nonlinear Dynamics; Phenotype; Polymorphism, Single Nucleotide - genetics; Psychological aspects; Psychology - statistics & numerical data; Psychometrics - statistics & numerical data; Reproducibility of Results; Risk Factors
• ISSN: 0007-1102; 2044-8317
• DOI: 10.1348/000711008X292343

Structural equation models (SEMs) have been widely applied to examine interrelationships among latent and observed variables in social and psychological research. Motivated by the fact that correlated discrete variables are frequently encountered in practical applications, a non‐linear SEM that accommodates covariates, and mixed continuous, ordered, and unordered categorical variables is proposed. Maximum likelihood methods for estimation and model comparison are discussed. One real‐life data set about cardiovascular disease is used to illustrate the methodologies.