My name is Joris Mulder. I work as an associate professor at the Department of Methodology and Statistics at Tilburg University. In my research I develop Bayesian statistical methods and software for applications in the social and behavioral sciences. I work on the following research topics.

• Relational event modeling of longitudinal social network data. Relational event history data contain information about who interacted with whom at what time. Our goal is to develop methods that allow us to better understand how interaction dynamics in a social network change over time based on this relatively new source of data. This work is supported by an ERC Starting Grant and a NWO Vidi Grant. I work on this topic together with Roger Leenders, Peter Hoff, Marlyne Bosman-Meijerink, Giuseppe Arena, Diana Karimova, and Mahdi Shafiee Kamalabad, among others. An introductory paper can be found here: Meijerink-Bosman et al. (2023) and R packages can be found here “remify“, “remstats“, “remstimate“, and developmental packages by the TilburgNetworkGroup.
• Bayes factor hypothesis testing. Another line of research focusses on developing (default) Bayes factors for testing (informative) hypotheses with equality and/or order constraints on the parameter of interest. The most recent contribution is the R package BFpack, which has been developed together with various colleagues (including Herbert Hoijtink, Xin Gu, Donald Williams, Caspar van Lissa, Florian Böing-Messing, among others). The relevant paper can be found here: Mulder et al. (2012). The package can be found on CRAN: BFpack. The package will be implemented in JASP in 2024. I am also co-developer of the R package bain (Gu et al. (2017), R package “bain”, JASP module)
• Bayesian Gaussian processes for nonlinear modeling. Nonlinearity is ubiquitous in (longitudinal) social research and Gaussian processes are a flexible methodology to learn nonlinear trajectories over time or nonlinear mechanisms between important variables. This line of research is funded by a ERC Consolidator Grant which will start in September 2024. A relevant paper can be found here: Mulder (2023).
• Other topics that I am working on include Bayesian network autocorrelation modeling (e.g., Dittrich at el., 2022 and R package “BANAM”), Bayesian regularization for variable selection problems (e.g., van Erp et al., 2019), Bayesian methods for clinical trial designs (e.g., Kavelaars et al. 2020), and Bayesian Gaussian graphical modeling (e.g., Williams & Mulder (2020) and R package “BGGM”), among others.

If you want to share your ideas or thoughts or if you have any questions about my work, feel free to email me at: j [dot] mulder3 [at] tilburguniversity [dot] edu.