networks
Definition
Networks refers to person-specific representations of psychological variables, such as symptoms, emotions, cognition, and behavior, in which the connections between those variables reflect temporal dynamics estimated from intensive longitudinal data. The connections are typically derived from vector autoregressive models, where lagged relationships capture how one variable at a given time point predicts another at the next. A central limitation of standard idiographic network models is the assumption of stationarity, meaning that neither the connections among variables nor their mean levels are permitted to change over time. The fixed moderated time series model addresses this by allowing all parameters of the VAR-based network, including the innovation structure and mean levels, to be moderated by contextual factors such as social interaction or sleep quality, as demonstrated in two patients receiving treatment for depression.
Sources: Bringmann et al. (2024)
Related Terms
- personalized models; moderation analysis (1 shared article)
- time series (1 shared article)
- vector autoregressive model (1 shared article)
Applications
Networks and Moderation
Moderation analysis within idiographic networks allows researchers to examine which contextual factors drive changes in network structure, rather than simply identifying when or where those changes occur. In the fixed moderated time series model, moderators such as daily stress, social interaction, or sleep quality can affect the lagged connections, the innovation structure, and the mean levels of variables simultaneously. This approach enables clinicians to test how specific interventions or life events influence the dynamic relationships among an individual's symptoms.
Sources: Bringmann et al. (2024)
Networks and Intensive Longitudinal Data
Idiographic psychological networks are constructed from intensive longitudinal data collected through methods such as Experience Sampling and Ecological Momentary Assessment, which capture emotional experiences and their fluctuations in daily life. As studies have extended to roughly 400 time points over periods exceeding four months in various patient groups, modeling change in mood, behavior, and cognition within the network has become the primary analytic interest. The volume and density of such data make it possible to estimate person-specific network structures and to detect how those structures shift in response to contextual factors.
Sources: Bringmann et al. (2024)
