cross-lagged panel design
Definition
Cross-lagged panel design refers to a longitudinal research approach in which two or more constructs are measured at two or more discrete measurement occasions typically separated by months or years, and in which variables at each occasion are regressed on variables at the previous occasion to estimate the predictive effect of each variable on others over a specific time lag while controlling for auto-regressive effects. In traditional applications, constructs of interest are modeled as latent variables underlying observed measures, though cross-lagged panel network models extend this approach to examine longitudinal associations among individual elements (e.g., symptoms, attitudes, or items) rather than among aggregated constructs. Cross-lagged paths represent the predictive strength of one variable on another at a later measurement occasion and may generate causal hypotheses, though such parameters do not themselves support causal inference. This design is most appropriate when researchers have data on several constructs at a limited number of discrete measurement occasions from a large group of individuals and when research questions center on predictive or potentially causal effects of these constructs over time.
Sources: Wysocki et al. (2025)
Related Terms
Applications
Cross-lagged Panel Design and Network Models
Cross-lagged panel network models extend network modeling approaches to longitudinal panel data collected at a small set of discrete measurement occasions. By analyzing direct relations between individual elements rather than aggregated latent constructs, this integrated approach reveals item-level longitudinal effects and identifies specific predictive pathways that may be missed by traditional latent variable cross-lagged panel models.
Sources: Wysocki et al. (2025)
