Projekt

The project aims at a theoretical foundation, development and application of robust procedures for risk management for complex systems in the presence of extreme events, i.e. identification, quantification, prediction and control of these risks. The elaborated method is applied to chosen reference applications. The examples consist of operational risk of a bank, unit length of stay and cost in intensive care of a university clinic, and river discharge data of Austrian rivers. Suitable parametric models for these contexts are developed. The goal is to adapt the shrinking neighborhoods approach to determine optimally-robust estimators minimizing the maximal asymptotic risk on neighborhoods about the ideal model and at the same time resulting in a high breakdown point. Furthermore, corresponding diagnostic tools to quantify and visualize the influence and outlyingness of data are developped.

• Dr. Peter Ruckdeschel

  Fraunhofer-Institut für Techno- und
  Wirtschaftsmathematik ITWM
  Abteilung Finanzmathematik
  Kaiserslautern
  

• Prof. Dr. Ralf Korn

  Rheinland-Pfälzische Technische
  Universität Kaiserslautern-Landau (RPTU)
  Fachbereich Mathematik
  AG Finanzmathematik
  Kaiserslautern
  

• Prof. Dr. Matthias Kohl

  Hochschule Furtwangen
  Fakultät Medical and Life Sciences
  Villingen-Schwenningen
  

• Dr. Bernhard Spangl

  Universität für Bodenkultur
  Wien
  Department für Raum, Landschaft und Infrastruktur
  Institut für Angewandte Statistik und EDV
  Wien
  Österreich