Robust Statistics for Cybernetics

Garant předmětu:

Lecturer:

Tutor:

Supervisor:

Department of Cybernetics

Synopsis:

Statistical methods are basic tools of control and decision making theory. Classical statistical methods (e.g. MLE) are usually very sensitive to deviations from our idealized model. Thus many methods which are robust have been developed. It means that these methods are not so sensitive to small deviations from an underlying model. So we briefly explain the parametric concept of estimation and then we introduce the robust approach, some basic robust estimators of location (e.g. trimmed mean, Hampel estimator) and measures of robustness (influence function, breakdown point).

Requirements:

Syllabus of lectures:

Syllabus of tutorials:

Study Objective:

Study materials:

Ricardo A. Maronna, R. Douglas Martin, Victor J. Yohai, Matías Salibián-Barrera, Robust Statistics: Theory and Methods (with R), 2nd Edition

ISBN: 978-1-119-21466-3 October 2018 464 Pages

Rousseeuw,P.J., Leroy,A. (1987) Robust Regression and Outlier Detection.

Wiley, New York

Huber,P.J. (1981) Robust Statistics.Wiley,New York

Hampel,F.R.,Ronchetti, E.M.,Rousseeuw, P.J.,Stahel,W.A. (1986) Robust

Statistics: The Approach Based on Influence Functions. Wiley,New York

Dodge,Y., Jureckova,J. (2000) Adaptive Regression. Springer, New York

Note:

Further information:

No time-table has been prepared for this course

The course is a part of the following study plans:

• Doctoral studies, daily studies (compulsory elective course)
• Doctoral studies, combined studies (compulsory elective course)
• Doctoral studies, structured daily studies (compulsory elective course)
• Doctoral studies, structured combined studies (compulsory elective course)