You are in the following website hierarchy:

Home
Research
You are here:Working Groups

Several hands placed together in a gesture of teamwork and unity, symbolizing collaboration and joint research effortts

Overview of Chairs and Working Groups

Learn more about the chairs and working groups at the department and their research work

A digital visualization featuring abstract polyhedrons in vibrant blue and purple tones.

Foundations Lab of Statistics and their Applications

We investigate the foundations of statistical inference and machine learning, focusing on applications where the available information is weakly structured. This comprises partial orders and other kinds of non-standard data as well as ambiguity about prior knowledge, preferences, or assumptions. Drawing conclusions including a proper uncertainty quantification in such scenarios is critical to modern statistics and data science.

Functional Data Analysis

We develop tools and methods to analyze functional data, i.e. curves and surfaces. We build user-friendly open-source software for both supervised and unsupervised tasks and prioritize transparent, reproducible research.

Rows of binary code (ones and zeros) in blue tones on a screen

Methods for Missing Data, Model Selection and Model Averaging

We have two main research topics: The tabular data with missing values and methods for the application of mutiple imputation methods, for model selection and model averaging techniques and for bootstrap resampling to receive confidence intervals with reasonable nominal coverage. Second, the Natural Language Processing (NLP), especially the evaluation and benchmarking of large language models and applications of the transformer architecture for combined text and visual problems.

Statistical Learning & Data science

The research groups within our chair explore a broad spectrum of domains, including automated machine learning, interpretable machine learning, causal inference, fair machine learning, deep learning, machine learning for survival analysis, methods beyond supervised learning, and natural language processing. Additionally, we are dedicated to developing user-friendly open-source software as part of our commitment to advancing the field.

Computational Statistics & Data Science

Our research is at the intersection of mathematical and computational statistics. We develop statistical methods, derive theoretical guarantees and scalable algorithms, package them in user-friendly software, and collaborate with domain experts to solve problems in diverse scientific fields.

A computer screen displaying code, diagrams, and graphical user interfaces, suggesting a programming or data environment.

Data Science

The Data Science group works at the intersection of statistics and machine learning with a particular focus on neural networks and optimization. Together with experts from other fields, we develop fast and scalable solutions for modeling complex data structures while simultaneously ensuring interpretability and the quantification of uncertainty.

A hand using a stylus on a digital tablet, with a semi-transparent overlay of a molecular or medical-style diagram.

Biomedical Statistics and Data Science

We are interested in developing and applying computational statistics and data science methods for the analysis of biological systems. We particularly focus on microbial ecosystems and their interplay with the host and the environment, including the human microbiome and marine ecosystems.

A DNA double helix composed of glowing golden and blue dots set against a dark, blurry background

Biostatistics

Our research is funded by the German Research foundations Heisenberg Program as well as the DFG project "Continuous Interventions in Epidemiology: from Theory to Practice". In these projects, causal inference methods for longitudinal continuous interventions are developed, and applied to (phamaco-)epidemiological questions.

Chair of Applied Statistics in Social Sciences, Economics and Business

The team works on methodological and algorithmic developments in the field of applied statistics. In particular, we conduct research on statistical modelling, network data analysis and the quantification of uncertainty in the field of machine learning. Interdisciplinary application areas include conflict research, rent indexes, remote sensing, telecommunication data as well as demography.

A laptop with a digital chart overlay in blue and purple showing upward and downward data curves, held by someone typing

Chair of Statistics and Econometrics

We study and develop statistical methods for creating empirical evidence in economics. Our research focuses on microeconometric methods such as identification and estimation of causal policy effects, inference for methods involving rankings, analysis of networks and peer-effects, nonparametric estimation and inference, and randomization inference.

Social Data Science and AI Lab

We are interested in all matters of social data science. Our growing team of researchers has different research focuses ranging from data quality and fairness in AI to the use of new data sources in the social sciences, multiple imputation methods, survey methodology, and statistical training.

Statistical Consulting Unit (StaBLab)

Our guiding principle is to improve the quality of empirical research across disciplines, by providing statistical consulting across all faculties of the LMU or external partners (companies, government agencies, etc.). We pursue a hands-on approach to research, often together other fields as life sciences, geosciences, political sciences, or ecology.

An abstract 3D mesh of glowing green and blue curved lines resembling digital waves or spatial structures on a dark background

Bayesian Imaging and Spatial Statistics

The Bayesian Image Analysis and Spatial Statistics group is focused on Bayesian methods and its applications. The latter include image processing and image analysis in medicine and biology, as well as spatial datasets in general.