Welcome to my site. I am an assistant professor at Penn State working as part of the Quantitative Developmental Systems Methodology group and also faculty at the Penn State Institute for CyberScience. My work centers on promoting scientific computing to answer complex questions in social and behavioral sciences.
In short, I aim to advance the use of models that capture individual differences in terms of person-specific process model parameters, and apply these models to large-scale (e.g., intensive longitudinal) data. These process models offer a framework for testing substantive theories by proposing concrete mechanisms that underlie observed data.
Currently I am focusing on developing dynamic models of well-being. In my lab we are conducting ecological momentary assessment (EMA) studies to collect intensive longitudinal data on people’s emotional experiences and cognitive evaluations of their daily life. By combining cognitive psychometric techniques and dynamical systems modeling, my goal is to unpack the mechanisms, pathways, and synchronicity dynamics of emotional and cognitive elements of well-being. Moreover, I am interested in studying how these well-being elements synchronize with physiological measures, such as blood volume pulse and electrodermal activity. The goal is to explore how person-specific patterns in these physiological variables can improve understanding of changes in self-reported well-being measures, and provide for deployment of real-time interventions.
The complexity of these models requires flexible methods for parameter estimation. Bayesian statistics offers these methods, while also providing a principled framework for statistical inference. Therefore an interwoven theme in my research is promoting Bayesian methods.
I earned my PhD at the University of Leuven. My doctoral dissertation focused on developing the Bayesian hierarchical bivariate Ornstein-Uhlenbeck (BHOU) model. I applied this model to changes in core affective states, measured intensively via self-reports in EMA studies. As a postdoc at the University of California, Irvine, I worked on developing a Bayesian statistical inference framework for various Cultural Consensus Theory (CCT) models. I am committed to building user-friendly software tools in order to facilitate broader adoption of these methods in applied research: two standalone computer programs (for BHOU and for CCT models) are available for download above.