The Bayesian Graphical Modeling Lab is dedicated to developing a Bayesian methodology for analyzing graphical models. In psychology, graphical models or networks are used to characterize dynamical systems of interacting psychological variables. Since the network structure is usually unknown, we must infer it from empirical data. As many structures could underlie a network of interest, we are usually uncertain that we have found the one true model for the data. The Bayesian approach provides a principled way to deal with this uncertainty by expressing the plausibility of different network structures, determining the statistical evidence for edge inclusion and exclusion, and providing robust prediction intervals for the network parameters. The Bayesian Graphical Modeling Lab is dedicated to bringing these advantages to end users through open-access publications and open-source statistical software in the form of R packages and by incorporating them into the free, easy-to-use JASP program.
Cascading Transitions Lab
The Cascading Transitions Lab is devoted to understanding cascading transitions in the context of behavioral and social sciences. In cascading transitions, individual transitions trigger or are triggered by social transitions. For example, one teenager might initiate a surge of smoking in their peer group.
The main objective of the lab is to reach an understanding of how these cascading transitions work, when they occur, and how they can be predicted, triggered, or prevented. To reach this objective, a formal modelling framework and an empirical approach for the study of cascading transitions in psychosocial systems will be developed. This methodology is then applied to four areas of social and behavioral sciences: opinion change, learning, addiction, and perception.
This highly interdisciplinary project is expected to stimulate future scientific research on cascading transitions in other disciplines, such as climate research, and to have significant impact on practices in conflict management, healthcare, and education.
The Theory Methods Lab is devoted to developing methodological tools that can assist scientists in theory construction. These methodological tools are centered on the formation of formalized theoretical systems that are implemented in mathematical models and computer simulations. The core idea that underpins the project is that scientific theories aim to explain robust empirical phenomena, and the process of constructing such explanatory systems can be organized in a coherent methodological framework. By representing both the theory and the phenomena in a formal model, these explanatory relations become transparent and can enter the public scientific space. As such, formalizing theories is a crucial element of open and transparent scientific practice.
Although the Theory Methods Lab is based in psychological science, as elements of theory construction methodology become mature, we intend them to be useful throughout the sciences. Conversely, we adapt and translate existing approaches that are well-developed in other fields for use in psychological science.