Robustness and Complex Data Structures

Presented in honor of Ursula Gather's 60th birthday this book deals with modern topics in the field of robust statistical methods, especially for time series and regression analysis, and with statistical methods for complex data structures.

This Festschrift in honour of Ursula Gather's 60th birthday deals with modern topics in the field of robust statistical methods, especially for time series and regression analysis, and with statistical methods for complex data structures. The individual contributions of leading experts provide a textbook-style overview of the topic, supplemented by current research results and questions. The statistical theory and methods in this volume aim at the analysis of data which deviate from classical stringent model assumptions, which contain outlying values and/or have a complex structure. Written for researchers as well as master and PhD students with a good knowledge of statistics.

Concise presentations of the relevant theory for the basic as well as up-to-date topics

Complex data structures beyond the pure treatment of robust methods

Robust methods for all fields of statistical analysis All contributions contain pointers to relevant algorithms and packages

Includes supplementary material: sn.pub/extras

Auteur

Prof. Dr. Claudia Becker is a Professor of Statistics at the Faculty of Law and Economics, Martin-Luther University Halle-Wittenberg. Her research priorities are robust statistical methods; robust statistical methods for dimension reduction in complex data structures; and statistical methods for regional economics to assess complex situations and relationships through interviews, with a particular focus on innovation and entrepreneurship research

Prof. Dr. Roland Fried has been a Professor of Statistics in Biosciences at the Faculty of Statistics, Dortmund University, since 2006. His research focuses on biostatistics; modeling spatial and temporal data; online monitoring; robust signal extraction and structural break detection, and efficient statistical computational algorithms

PD Dr. Sonja Kuhnt has held a temporary professorship at the Institute for Mathematical Statistics with Applications in Industry, Faculty for Statistics, TU Dortmund University, since 2008. Her present research fields are robust methods for categorical data and graphical models; computer algebra in statistics; offline planning of industrial processes; and acquisition of information in logistics

Contenu
Part I Univariate and Multivariate Robust Methods: Multivariate Median (Hannu Oja).- Depth Statistics (Karl Mosler).- Multivariate Extremes: A Conditional Quantile Approach ( Marie-Françoise Barme-Delcroix).- High-Breakdown Estimators of Multivariate Location and Scatter (Peter Rousseeuw and Mia Hubert).- Upper and Lower Bounds for Breakdown Points (Christine H. Müller).- The Concept of -outliers in Structured Data Situations (Sonja Kuhnt and André Rehage).- Multivariate OutlierIidentification Based on Robust Estimators of Location and Scatter (Claudia Becker, Steffen Liebscher and Thomas Kirschstein).- Robustness for Compositional Data (Peter Filzmoser and Karel Hron).- Part II Regression and Time Series Analysis: Least Squares Estimation in High Dimensional Sparse Heteroscedastic Models (Holger Dette and Jens Wagener).- Bayesian Smoothing, Shrinkage and Variable Selection in Hazard Regression (Susanne Konrath, Ludwig Fahrmeir and Thomas Kneib).- Robust Change Point Analysis (Marie Huková).- Robust Signal Extraction From Time Series in Real Time (Matthias Borowski, Roland Fried and Michael Imhoff).- Robustness in Time Series: Robust Frequency Domain Analysis (Bernhard Spangl and Rudolf Dutter).- Robustness in Statistical Forecasting (Yuriy Kharin).- Finding Outliers in Linear and Nonlinear Time Series (Pedro Galeano and Daniel Peña).- Part III Complex Data Structures: Qualitative Robustness of Bootstrap Approximations for Kernel Based Methods (Andreas Christmann, Matías Salibián-Barrera and Stefan Van Aels).- Some Machine Learning Approaches to the Analysis of Temporal Data (Katharina Morik).- Correlation, Tail Dependence and Diversification (Dietmar Pfeifer).- Evidence for Alternative Hypotheses (Stephan Morgenthaler and Robert G. Staudte).- Concepts and a Case Study for a Flexible Class of Graphical Markov Models (NannyWermuth and David R. Cox).- Data Mining in Pharmacoepidemiological Databases (Marc Suling, Robert Weber and Iris Pigeot).- Meta-Analysis of Trials with Binary Outcomes (JürgenWellmann).