In 2022, I gave a workshop on Bayesian Structural Equation Modeling during the conference SEM: New Developments and Applications. Materials for this workshop are available on GitHub.
I have taught work groups in various methodology and statistics courses since 2012, first as student-assistant and later as a PhD candidate. As Assistant Professor at Utrecht University, I have (co-)coordinated and taught in various methodology and statistics courses, including the Bayesian summer school course for which all materials are available online.
I am co-promotor and daily supervisor of Aliasghar Rostami Charati on a project in which Bayesian regularization methods are developed for Relational Event Models (REMs).
I am co-promotor and daily supervisor of Florian van Leeuwen on the project: “Getting the best predictions from complex data sets: Balancing scalability and interpretability”. The goal of this project is to bridge the gap between the scalability of predictive modeling techniques and their interpretability by combining rigorous statistical methods with innovative machine learning approaches.
I am co-promotor and daily supervisor of Sanne Appels on the interdisciplinary Road to Resilience project. The goal of this project is to uncover protective factors and compensatory mechanisms behind resilient trajectories in atypical literacy acquisition using Bayesian (regularized) SEM.
Jonathan Koop (2025). Refining Relational Event Models: Bayesian Penalization and Variable Selection in REMs. All code available on Github.
Zhipei (Kim) Wang (2025). Comparing Bayesian Post-estimation Variable Selection Methods: Projection Predictive Variable Selection Versus Stochastic Search Variable Selection. All code available on Github.
Michael Koch (2022). Getting a Step Ahead: Using the Regularized Horseshoe Prior to Select Cross-Loadings in Bayesian CFA. All code available on GitHub.
Ylias Ben Salah (2021). A Comparison between Bayesian penalized regression priors: Lasso and regularized horseshoe.
Rashied Amir (2021). The key differences between the classic and Bayesian LASSO: Comparing shrinkage and variable selection properties in regression problems.