Developing contemporary mathematical statistics
The objective of the group is to develop new robust substitutes to classical statistical methods such as maximum likelihood, least squares and Bayesian methods.
Robust strategies
Classical statistical methods are designed to provide good estimators when the statistical model is exact. When the model is only approximate, these estimators may perform poorly. Unfortunately, in general all we can expect is that the statistical model provides a suitable approximation of reality. Our group aims at designing reliable procedures in the situation where the model may only be approximate.
Head of Group
