C
Christophe Ley
Researcher at Ghent University
Publications - 148
Citations - 4974
Christophe Ley is an academic researcher from Ghent University. The author has contributed to research in topics: Estimator & Stein's method. The author has an hindex of 23, co-authored 145 publications receiving 3661 citations. Previous affiliations of Christophe Ley include Vrije Universiteit Brussel & Université libre de Bruxelles.
Papers
More filters
Journal ArticleDOI
Detecting outliers: Do not use standard deviation around the mean, use absolute deviation around the median
TL;DR: In this article, the authors highlight the disadvantages of this method and present the median absolute deviation, an alternative and more robust measure of dispersion that is easy to implement, and explain the procedures for calculating this indicator in SPSS and R software.
Journal ArticleDOI
Detecting multivariate outliers: Use a robust variant of the Mahalanobis distance
TL;DR: A variant based on the Minimum Covariance Determinant, a more robust procedure that is easy to implement and demonstrates the detrimental impact of outliers on parameter estimation and shows the superiority of the MCD over the Mahalanobis distance.
Book
Modern Directional Statistics
Christophe Ley,Thomas Verdebout +1 more
TL;DR: This book discusses uniformity tests based on random projections, as well as local asymptotic normality and optimal testing LAN for directional data, and discusses flexible parametric distribution theory in more detail.
Journal ArticleDOI
How to classify, detect, and manage univariate and multivariate outliers, with emphasis on pre-registration
TL;DR: A functional definition of outlier detection methods is provided and the use of the median absolute deviation to detect univariate outliers, and of the Mahalanobis-MCD distance to detect multivariate outlier outliers is recommended.
Journal ArticleDOI
Stein's method for comparison of univariate distributions
TL;DR: In this article, a new general version of Stein's method for univariate distributions is proposed, which is based on a linear difference or differential-type operator, and the resulting Stein identity highlights the unifying theme behind the literature on Stein's methods both for continuous and discrete distributions.