Tackling Challenges in Data Pooling: Missing Data Handling in Latent Variable Models with Continuous and Categorical Indicators

• Published in: Structural equation modeling Vol. 31; no. 4; pp. 651 - 666
• Main Authors: Chen, Lihan, Miočević, Milica, Falk, Carl F.
• Format: Journal Article
• Language: English
• Published: Hove Routledge 03.07.2024; Psychology Press
• Subjects: Correlation; Data analysis; Data synthesis; Discriminant analysis; Factor Analysis; Least Squares Statistics; Maximum Likelihood Statistics; Measurement errors; Mediation; missing data; nonnormal data; ordinal data; pooled data analysis; Simulation; Statistical methods
• ISSN: 1070-5511; 1532-8007
• DOI: 10.1080/10705511.2023.2300079

Data pooling is a powerful strategy in empirical research. However, combining multiple datasets often results in a large amount of missing data, as variables that are not present in some datasets effectively contain missing values for all participants in those datasets. Furthermore, data pooling typically leads to a mix of continuous and categorical items with nonnormal multivariate distributions. We investigated two popular approaches to handle missing data in this context: (1) applying direct maximum likelihood by treating data as continuous (con-ML), and (2) applying categorical least squares using a polychoric correlation matrix computed from pairwise deletion (cat-LS). These approaches are available for free and relatively straightforward for empirical researchers to implement. Through simulation studies with confirmatory factor analysis and latent mediation analysis, we found cat-LS to be unsuitable for pooled data analysis, whereas con-ML yielded acceptable performance for the estimation of latent path coefficients barring severe nonnormality.