How well do Network Models predict Observations? On the Importance of Predictability in Network Models

TL;DR

This paper emphasizes the importance of predictability in network models for psychological phenomena, introducing nodewise predictability to assess how well nodes can be forecasted by their connected nodes, with practical applications in clinical settings.

Contribution

It introduces nodewise predictability as a new metric for evaluating network models' predictive accuracy, filling a gap in current methodological approaches.

Findings

Nodewise predictability quantifies how well a node can be predicted by its neighbors.

Provides reproducible code for computing and visualizing predictability.

Highlights the relevance of predictability for clinical interventions.

Abstract

Network models are an increasingly popular way to abstract complex psychological phenomena. While the study of the structure of network models has led to many important insights, little attention is paid to how well they predict observations. This is despite the fact that predictability is crucial for judging the practical relevance of edges: for instance in clinical practice, predictability of a symptom indicates whether a an intervention on that symptom through the symptom network is promising. We close this methodological gap by introducing nodewise predictability, which quantifies how well a given node can be predicted by all other nodes it is connected to in the network. In addition, we provide fully reproducible code examples of how to compute and visualize nodewise predictability both for cross-sectional and time-series data.