October 2026
Homepage Release!!
Release
Dr. Marléne Baumeister
I am a PostDoc in the working group of Prof. Dr. Markus Pauly. Currently, I am working in the DFG-funded project pOwerful fUnctional daTa CompLex fActorial deSignS (OUTCLASS) together with Prof. Dr. Łukasz Smaga and Natalia Stefańska from Adam Mickiewicz University, Poznań, Poland. We develop new methods for both univariate and multivariate functional repeated measures ANOVA and ANCOVA that are not constrained by traditional model assumptions.
- I studied Mathematics and Philosophy in Bielefeld and Statistics in Dortmund. My dissertation defence was in September 2025.
- During my PhD, I started to learn Empirical Process Theory and I successfully applied it to create a quantile-based MANOVA. Since then, I like to create useful and reliable statistical methods out of mathematical theory.
- I am a cycling enthusiast and I know everything about eventing, which is a kind of equestrian sports.
News
September 2026
Markus Pauly and I visited Poznań for a research meeting in the OUTCLASS project. Read the article at the RC Trust homepage.
Research Stay
September 2026
I gave a talk at the IBS-DR Workshop on Multivariate and Functional Data Analysis in Biostatistics. Find the article at the university’s homepage and my presentation.
Talk
August 2026
Together with Markus Pauly, I supervised Enes Ün during his Erasmus+ internship. We worked on a simulation study about MANOVAs. Find the article at the RC Trust Homepage.
Supervision
Highlights
WEAVE NCN-DFG Project OUTCLASS: Powerful Inference for Functional Data in Complex Factorial Designs
The DFG-funded project I am currently working on.
Resampling-Based Inference for Incomplete Paired Functional Data
arXiv-Preprint about handling two-sided missingness in paired functional data.
Why is Regularization Underused? An Empirical Study on Trust and Adoption of Statistical Methods
arXiv-Preprint about a survey that investigates how statistical practitioners use innovative statistical methods.
Dissertation: Empirical process theory for robust inference in multivariate analyses and multiple testing
This cumulative dissertation is about multivariate and multiple testing methods which are applicable for data beyond normality.
Workshop on Git and Project Management
Originally for a workshop at the Department of Statistics of TU Dortmund University, I created this slides together with my colleague Mark Joachim Krallmann.
Research Interests
Robust Multivariate Testing Procedures
I create inference procedures for global and local hypotheses in complex multivariate factorial designs on quantiles, for functional data, and with covariate-adjusted means. Find examples below.
Resampling-based Statistical Inference
I use resampling techniques to create theoretically valid inference procedures that are more robust than established methods. Find examples below.
The Use of Statistics in Practice: Which Method in Certain Situations?
I create extensive comparative simulations studies that allow detailed insights into advantages and disadvantages of certain statistical methods. This allows me to give detailed recommendations of the use statistical methods. Find examples below.
Exploring the Needs of Practitioners
I participated in a survey that investigates why statistical practitioners use or not use methods of regularization in their analyses. The project was supported by the Research Center Trustworthy Data Science and Security (RC Trust). Find a preprint below.