Nonparametric tests of symmetry for non-elliptical distributions

0491756 - ÚI 2019 BE eng A - Abstract
Kalina, Jan - Šiman, Miroslav
Nonparametric tests of symmetry for non-elliptical distributions.
ICORS 2018. Book of Abstracts. Leuven, 2018. s. 122-122.
[ICORS 2018. International Conference on Robust Statistics. 02.07.2018-06.07.2018, Leuven]
Institutional support: RVO:67985807 ; RVO:67985556
Keywords : Robust estimation * Multivariate data * Location and scatter * Shape estimator * Symmetry test
OECD category: Statistics and probability
https://wis.kuleuven.be/events/icors18/BookOfAbstracts

The basis for our work is a theoretical result explaining how various multivariate location and scatter estimators capture the symmetry of the underlying distribution. Various forms of symmetry considered in the paper include central symmetry, marginal symmetry, symmetry around an affine subspace, and symmetry around a coordinate axis. Very general sufficient conditions are formulated, which ensure various symmetry properties of functionals corresponding to location or scatter. There is a variety of robust multivariate estimators, which fulfil these sufficient conditions.
Permanent Link: http://hdl.handle.net/11104/0285396