Cross-Lagged Network Models

Network theory and accompanying methodology are becoming increasingly popular as an alternative to latent variable models for representing and, ultimately, understanding psychological constructs. The core feature of network models is that individual observed items (e.g., symptoms of depression) are allowed to directly influence each other, resulting in an interconnected system of items. The dynamics of such a system give rise to emergent states of constructs (e.g., a depressive episode). Network modeling has been applied to cross-sectional data and intensive longitudinal designs (e.g., data collected using an Experience Sampling Method). Currently lacking in the methodological toolbox of network modeling is a method with the capacity to estimate network structures at the item level on longitudinal data with relatively few measurement occasions. As such, in this paper, we present a cross-lagged panel network model to reveal item-level longitudinal effects that occur within and across constructs over time. The proposed model uses a combination of regularized regression estimation and SEM to estimate auto-regressive and cross-lagged pathways that characterize the effects of observed components of psychological constructs on each other over time. We demonstrate the application of this model to longitudinal data on students’ Commitment to School and Self-Esteem.