Mathisca de Gunst

Home page Mathisca de Gunst

Prof.dr. M.C.M. de Gunst
Department of Mathematics
Faculty of Science
Vrije Universiteit Amsterdam
De Boelelaan 1111
1081 HV Amsterdam
e-mail: m.c.m.de.gunst@vu.nl

I am a professor emerita in the Statistics Group of the Department of Mathematics of the Vrije Universiteit Amsterdam.

Research
Software
Links

Research

My research is in the area of stochastic modeling and statistical analysis of biological processes, and comprises development, assessment and application of statistical models and tools. I use mathematical models ranging from (non)linear regression, Markov and hidden Markov models to non-Markovian counting processes, and frequentist as well as Bayesian estimation techniques. My main interest is in statistical models for networks with a special focus on neuroscience applications.

Current research projects

Statistical inverse problems for network dynamics
Modeling and statistics for brain network dynamics

Past research projects

Modeling and statistics for gene regulatory networks
Statistics for the blood coagulation system
Statistics for neuronal network formation
Modeling the gene network underlying neuronal outgrowth
Statistical analysis of spatiotemporal patterns of activity in neuronal networks
Statistics for ion channel kinetics
Carcinogenesis modeling
Modeling plant cell population growth

Publications
See this page.

Statistics Group

Staff members
Paulo de Andrade Serra
Eduard Belitser
Philip Boeken
Marc Corstanje
Camilla Damian
Mathisca de Gunst
Rikkert Hindriks
Frank van der Meulen
Stephanie van der Pas
Wessel van Wieringen

PhD students
Adel Magra
Huixiaqing Liu
Tijn Jacobs
Julia Kowalska
Luminita Maxim
Nadja Rutsch
Yury Tavyrikov
Alexandra Vegelien

Software

Some software developed by our group

Cov3KP (Ros, 2015):
algorithm for estimating the covariance matrix of a matrix variate normal model where the covariance matrix is a Kronecker product of three components.
Accompanying paper.
GEMULA (Geeven, 2012):
method for identification of context-specific gene regulatory networks based on linear models and parameter estimation using lasso.
Accompanying paper.
LLM3D (Geeven, 2011):
log-linear modeling-based method to predict functional gene regulatory interactions from genome-wide expression data.
Accompanying paper.