Hello!

I am a third-year PhD student at the University of Zurich in the Psychological Methods department, supervised by Rudolf Debelak. My research focuses on developing new methods for planning empirical studies, with a particular interest in using machine learning techniques. In my free time, I enjoy climbing, cycling, and eating lots of Korean ramen.

Projects

On this page, you can find a short overview of my current projects. If you have any questions or are interested in collaborating with me, please feel free to get in touch.

Applications of Machine Learning in Psychology

Machine learning is increasingly gaining a foothold as a tool for psychological research. In my master's thesis, I summarized the applications along the different subfields. Especially in image or text processing, I found that machine learning - especially deep learning - has great potential. To keep up with the latest developments and practice some teaching, I held a seminar in 2022 specifically on the applications of deep learning in psychology [open materials in German]. In the future, I want to expand on and publish a part of my master's thesis that applies natural language processing.

Statistical Power Analysis for Item Response Theory Models

Some common psychometric models and hypothesis tests lacked formulas for determining statistical power as a function of sample size. We suggested and evaluated such formulas and made them available in an R package. Further evaluation of the new methods is currently ongoing as part of a master's thesis. A potential next step in this project is to write a tutorial.

Sample Size Planning for Complex Study Designs

The relation of sample size and statistical power can be hard to describe mathematically, especially when we look at more complex study designs. Modern designs can have multiple sample sizes, for example for separate arms or stages of a clinical trial. We developed an approach to estimate the sample sizes in these cases efficiently, while taking the cost of the overall study design into account. Our approach builds on simulations combined with machine learning methods. It's available in an R package along with a tutorial. Going forward, I want to refine this method and its implementation.

Sample Size Planning for Validating Clinical Prediction Models

Once a clinical prediction model has been developed using an initial data set, its predictive performance needs to be validated using new data. The sample size for this validation needs to be planned with the precision of the performance measurement in mind. In recent years, some methods have been proposed to solve this problem. During my current visit with Daniel Stahl at King's College London, we aim to contribute to this growing pool of methods.