Loughborough University
Leicestershire, UK
LE11 3TU
+44 (0)1509 263171
Loughborough University

Loughborough University Institutional Repository

Please use this identifier to cite or link to this item: https://dspace.lboro.ac.uk/2134/23634

Title: Geometric aspects of robust testing for normality and sphericity
Authors: Richter, Wolf-Dieter
Strelec, Lubos
Ahmadinezhad, Hamid
Stehlik, Milan
Keywords: Huberization
Trimming
Lehman-Bickel functional
Monte Carlo simulations
Power comparison
Robust tests for normality
Normality
Sphericity
Issue Date: 2017
Publisher: © Taylor & Francis
Citation: RICHTER, W-D. ...et al., 2017. Geometric aspects of robust testing for normality and sphericity. Stochastic Analysis and Applications, 35 (3), pp. 511-532.
Abstract: Stochastic Robustness of Control Systems under random excitation motivates challenging developments in geometric approach to robustness. The assumption of normality is rarely met when analyzing real data and thus the use of classic parametric methods with violated assumptions can result in the inaccurate computation of pvalues, e↵ect sizes, and confidence intervals. Therefore, quite naturally, research on robust testing for normality has become a new trend. Robust testing for normality can have counter-intuitive behavior, some of the problems have been introduced in [46]. Here we concentrate on explanation of small-sample e↵ects of normality testing and its robust properties, and embedding these questions into the more general question of testing for sphericity. We give geometric explanations for the critical tests. It turns out that the tests are robust against changes of the density generating function within the class of all continuous spherical sample distributions.
Description: This paper is in closed access until February 2018.
Version: Accepted for publication
DOI: 10.1080/07362994.2016.1273785
URI: https://dspace.lboro.ac.uk/2134/23634
Publisher Link: http://dx.doi.org/10.1080/07362994.2016.1273785
ISSN: 1532-9356
Appears in Collections:Closed Access (Maths)

Files associated with this item:

File Description SizeFormat
Geometric_aspects.pdfAccepted version682.01 kBAdobe PDFView/Open

 

SFX Query

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.