The goal of robust statistics is to develop data analytical methods which are resistant to outlying observations in the data, and hence which are also able to detect these outliers. The initial work by Huber (1981), Hampel et al. (1986) and Rousseeuw and Leroy (1987) mainly focused on estimators for location, scale, scatter and regression.
Nowadays, robust estimators are being developed for many more statistical models. Our research group is active in investigating estimators of covariance and regression for high-dimensional data, with applications in chemometrics, bio-informatics and actuarial sciences. Robust estimators have been developed for PCA (principal component analysis), PCR (principal component regression), PLS (partial least squares), classification, ICA (independent component analysis), multi-way analysis and other multivariate models. Recent research interests are robust inference, statistical depth, functional data and cellwise outliers.
Our research group currently consists of the following people:
Former members include Guy Brys, Michiel Debruyne, Sanne Engelen, Eric Schmitt, Kaveh Vakili, Karlien Vanden Branden, Stephan Van der Veeken, Johan Van Kerckhoven, Dina Vanpaemel and Sabine Verboven.
This website provides a complete list of our publications as well as corresponding software. A large number of robust methods for low- and high-dimensional data-analysis is collected in our Matlab toolbox LIBRA.