Open Science, Meta-Science, and Statistics
For me, one of the most fun aspects of doing research is learning new methods and sharing these methods with other people. Throughout my studies and PhD, I had the opportunity to learn from and collaborate with various methodologists and statisticians and to contribute to various research lines.
In a first research line, I explored the impact of data pre-processing decisions on statistical outcomes. We found that data pre-processing decisions massively influence statistical results and theoretical conclusions (Primbs, Holland, Quandt, & Bijlstra, in prep.) and provide a checklist (Loenneker et al., 2024) for transparent data pre-processing. I also frequently give talks on data pre-processing and multiverse analyses and developed a Shiny app for teaching about data pre-processing.
In a second research line, I’m thinking about effect size interpretation. What does an effect size actually mean? And what is the smallest effect size I care about, the smallest effect size of interest? In a first paper, we caution readers against misinterpreting effect sizes and highlight the importance of interpretating effect sizes relative to meaningful comparison standards (Primbs et al., 2024a). We continue this research line by arguing for the need for consensus meetings to establish field-specific smallest effect sizes of interest (Primbs et al., 2024b) and providing tools for establishing a smallest effect size of interest for researchers with little statistical training (Peetz et al., 2024)
Currently, I’m learning about causal inference and am sharing my newly learned knowledge by writing tutorials on causal inference methods aimed at people new to causal inference (Primbs et al., 2024c).
I also regularly contribute to large team science projects and serve as Assistant Director for Translation and Cultural Diversity at the PSychological Science Accelerator. In this capacity, I have contributed to many large-scale research projects, including two last-authored projects in PNAS and Nature Scientific Data.