Beyond Homogeneity: Exploring Causal Heterogeneity in Psychopathology

Traditional models in psychiatric research often impose assumptions of causal homogeneity, treating population-level associations as reflective of uniform underlying mechanisms. This dissertation challenges that assumption by introducing statistical and machine learning frameworks designed to detect and model causal heterogeneity in the development of psychopathology. Central to this approach is the advancement of finite mixture structural equation modeling (FM-SEM) to identify latent subgroups characterized by distinct, and sometimes opposing, causal pathways. The dissertation comprises three integrated empirical studies. The first introduces mixDoC, a finite mixture extension of the classical Direction of Causation (DoC) model applied to twin data, enabling the detection of subpopulations with divergent causal directions between executive function and internalizing symptoms. The second presents mixCLPM, a longitudinal mixture model that captures subgroup-specific temporal dynamics and cross-lagged influences. The third transitions to a predictive modeling framework using Tabular Variational Autoencoders (TVAEs) to generate synthetic data, improving the detection and prediction of developmental risk profiles. Across these studies, findings demonstrate that traditional modeling approaches often obscure meaningful subgroup variation, potentially leading to inaccurate or incomplete inferences about etiology. By integrating causal modeling, longitudinal analysis, and synthetic data–enhanced prediction, this work provides a unified methodological framework for studying psychiatric heterogeneity and supports ongoing efforts in precision psychiatry.