The Bayesian Reanalysis Project
The Bayesian Re-analysis Project aims to assess the robustness of psychological networks. To achieve this goal, the project collects the data used in published cross-sectional network analyses and reanalyzes each dataset using standardized frequentist and Bayesian procedures. How robust are frequentist network results? What are the patterns in the structure of psychological networks? On the one hand, the project aims to demonstrate the advantages of the Bayesian approach to network analysis, and on the other hand, it aims to answer the field's burning questions about the structure of psychological networks. The Bayesian Re-Analysis Project project is led by Karoline Huth, Jonas Haslbeck, and Maarten Marsman.
The Brain - Behavior Network Project
Network science has provided many insights into brain and behavioral function, but mostly in parallel. The Brain-Behavior Network Project aims to improve our understanding of brain-behavior interactions by integrating brain and behavioral networks. To achieve this goal, we use a Bayesian hierarchical approach that models the connection between graphical models using random graphs. This allows us to bridge the gap between idiographic (individual) and cross-sectional networks and to integrate brain and behavioral networks. We validate our model in a large ADHD cohort. The project is led by Maarten Marsman, Anouk Schrantee, and Tessa Blanken.
The Bayesian Graphical Modeling Project
The Bayesian Graphical Modeling project outlines a new research program for psychological network modeling that addresses current methodological challenges. Based on the basic principles of Bayesian inference, a new confirmatory network methodology will be developed that uses model-averaging to provide robust, replicable network results. The new model-averaging approach will be designed for an exhaustive collection of network models and for cross-sectional and longitudinal applications. To increase the impact of the project, the new methods and models will be made available in JASP (jasp-stats.org). The Bayesian Graphical Modeling Project is led by Maarten Marsman.