We are a dynamic hub for research in mathematical statistics. Much of our current research is motivated by challenges from other academic disciplines and real-world businesses. Our work focuses on developing versatile ideas and methods with broad applications in science, industry, and society. We specialize in developing stochastic models and statistical methods for analyzing spatiotemporal data, functional data, and high-dimensional genomics data.
Read about our research projects
Read about the joint statistical seminar series
Publications in Mathematical Statistics
Biostatistics and bioinformatics conducts research into developing of statistical theory and methods, implementing software tools and conducting applied analyses – all related to problems within the field of life science.
Functional Data Analysis and Spatial Statistics conducts research in functional data analysis and spatial statistics, working with modeling, prediction and nonparametric inference.
Geometric Deep Learning research in geometric deep learning is concerned with investigating the role of symmetries and other geometric structures in the context of deep learning.
Mathematical Programming develops theory, methods, and software for efficiently solving optimization and decision problems using modern computing systems.
Statistical Learning and Inference for Spatio-Temporal Data Research in this research group includes signal/image analysis and statistical learning and inference for spatio-temporal data.
Semiparametric regression and numerical methods are interested in developing scalable methods for fitting generalized additive models with various shape constraints.
Our research links naturally to research activities at campus, including CLiC, CMTF, IceLab and UMIT, and also at our neighbour university, SLU. We have access to advanced infrastructure at HPC2N and resources at BILS and SciLifeLab. We contribute to Umeå University's strong tradition in empirical sciences and big data analysis that are produced within several research units on campus, including UCMR, UPSC, Radiation Sciences, and Cloud and Grid Computing.
We actively welcome collaboration. Feel free to reach out if you're interested in a research visit, working on a thesis project, or attending our seminars.
Present research areas in mathematical statistics can be shortly described by the following two lists of keywords:
Classification and cluster analysis
Computer intensive methods such as bootstrap and subsampling
Functional data analysis
Hidden Markov models
Marked spatial point processes
Maximum spacing methods
Non-parametric statistics, nearest neighbour methods
Numerical analysis and simulation of random functions
Quantization of random processes and sequences
Spatial statistics and statistical imaging
Statistical learning
Time series analysis and statistical signal processing, time-frequency analysis
Biostatistics and bioinformatics
Biomedical engineering
Compressive sensing
Computational statistics
Digital signal processing for audio conferencing systems
Environmetrics
Forest science
Human movement analysis
Limnology
Medical imaging
Population biology
Remote sensing and environment
Skeletal muscle characterisation
Sport science
Wavelets in signal and image analysis
