Maarten Marsman, University of Amsterdam

2024 Early Career Award

Nearly two decades ago, a new conceptual model for relating observations to theoretical constructs emerged in the psychometric literature: The network model. This new conceptual approach spread rapidly throughout the psychological sciences, catalyzed by the rapid development of methodology and accompanying software that allowed psychologists to fit these network models to their own data. The early stages of the psychometric network literature were marked by considerable methodological advances, the establishment of formal links between the new network models and classical latent variable models such as factor and item response theory models, and the revival of classical psychometric debates (e.g., the idiographic vs. nomothetic debate) and divisions (the parallel literatures on structural equation modeling and item response theory modeling).

But as the field has matured, several methodological and conceptual concerns have emerged. I will focus on what I consider to be the two biggest challenges facing the field: ensuring the robustness of network results, and developing longitudinal and cross-sectional models that fit the mostly discrete data we see in practice. My research program aims to address these challenges by using Bayesian model averaging to account for model uncertainty, which is at the heart of robustness concerns, and by using established links to classical psychometric theory to develop network models that fit psychological data. This research will build on previous developments and emphasize the importance of open source and user-friendly software for broader adoption of these methodological advances. In addition, the new modeling solutions inspired by formal links to classical psychometric models will have implications for ongoing debates and divisions within the evolving field of psychometrics.

About the Speaker

Maarten Marsman is an Assistant Professor at the Psychological Methods Unit of the University of Amsterdam. He received his PhD from the University of Twente in 2014, after which he became a postdoctoral researcher at the Psychological Methods Unit, where he established the Bayesian Graphical Modeling Lab (https://bayesiangraphicalmodeling.com). Maarten’s research combines psychometric theory with cutting-edge Bayesian inferential and computational methods, focusing on the Bayesian analysis of psychological data in general, and graphical network models in particular. Together with his team, he has worked extensively on developing the Bayesian approach to graphical network modeling of discrete psychometric data. Maarten’s research has been funded by the Dutch Research Council (NWO) and the European Research Council (ERC). In addition to his research, he has contributed to the development of the open-source statistical software JASP, which incorporates frequentist and Bayesian methods for common statistical analyses, and to several R software packages. He is also an enthusiastic teacher of Bayesian and computational statistical methods.