Statistics and data analysis

Organisation profile:The need to analyze data occurs in many situations. In the natural sciences, the objective is often to discover structures and underlying patterns. In medical and pharmaceutical work, one wants to determine the most effective drug or treatment. In economics and business one tries to make predictions, as accurately as possible. In computer science and engineering, huge amounts of data need to be analyzed for computer vision, data mining, and real-time process control. For these and other tasks many statistical methods exist, involving estimating and testing, regression, time series analysis, clustering, discriminant analysis, etc. Our research focuses on the construction of robust versions of such methods, which can withstand outliers, contamination, or other artefacts. Apart from the methodological aspect, much emphasis is on the implementation of these techniques by means of algorithms and corresponding software. Our main motivation is in terms of practical applications, and a sizeable part of our work originated from collaborations with other fields.

Keywords:CLUSTER ANALYSIS, ROBUST STATISTICS, STATISTICAL TECHNIQUES, STATISTICAL COMPUTING, ALGORITHMS

Disciplines:Applied mathematics in specific fields, Statistics and numerical methods, Computer architecture and networks, Distributed computing, Information sciences, Information systems, Programming languages, Scientific computing, Theoretical computer science, Visual computing, Other information and computing sciences