EUVIMEDEUVIMED entdecken
Crossref

On the Use of M-Quantiles for Outlier Detection in Multidimensional Data

Sajal Chakroborty, Ram Iyer, A. Alexandre Trindade

Mathematical Methods of Statistics · 2026-06 · 35 (2) · 104-123

DOI: 10.3103/s1066530726700080 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Mathematical Methods of Statistics, online erschienen am 10.08.2026. Verfasst von Sajal Chakroborty und 2 weiteren Autor:innen. Die Arbeit nennt 52 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Defining the notion of a multivariate quantile has been an open problem for more than half a century, motivating a plethora of possible solutions. Of these, the approach of Chakraborty and Chaudhuri [8] and Koltchinskii [26] leading to M-quantiles, is very appealing for its mathematical elegance, combining elements of convex analysis and probability theory. The key idea is the description of a convex function (the K-function) whose gradient (the K-transform) is in one-to-one correspondence between all of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\mathbb{R}^{d}$$\end{document} and the unit ball in \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\mathbb{R}^{d}$$\end{document}. By analogy with the \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$d=1$$\end{document} case where the K-transform is a cumulative distribution function like object (an M-distribution), the fact that its inverse is guaranteed to exist lends itself naturally to providing the basis for the definition of a quantile function for all \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$d\geq 1$$\end{document}. The resulting M-quantiles have seen applications in a variety of fields, with outlier detection featuring prominently. We show that for odd \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$d\geq 3$$\end{document} it is not the first derivative, but a poly-Laplacian of the K-function that is proportional to the density function. (For even values of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$d$$\end{document} no relationship is apparent.) Two-dimensional examples from non-standard distributions reinforce this point, and illustrate a feature of the K-transform whereby high density regions of the support are mapped to larger volumes, thereby producing a magnification effect that moves inliers closer to the boundary than outliers. In conclusion, the K-transform should not be viewed as a distribution function in higher dimensions, and its inverse does not lead to a ‘‘useful’’ quantile function, in the sense that its level set contours do not plausibly delineate outlying regions.

Zitieren

APA

Chakroborty, S., Iyer, R., & Trindade, A. A. (2026). On the Use of M-Quantiles for Outlier Detection in Multidimensional Data. Mathematical Methods of Statistics, 35(2), 104-123. https://doi.org/10.3103/s1066530726700080

Vancouver

Chakroborty S, Iyer R, Trindade AA. On the Use of M-Quantiles for Outlier Detection in Multidimensional Data. Mathematical Methods of Statistics. 2026;35(2):104-123. doi:10.3103/s1066530726700080

BibTeX
@article{Chakroborty2026,
  author = {Chakroborty, Sajal and Iyer, Ram and Trindade, A. Alexandre},
  title = {On the Use of M-Quantiles for Outlier Detection in Multidimensional Data},
  journal = {Mathematical Methods of Statistics},
  year = {2026},
  volume = {35},
  number = {2},
  pages = {104--123},
  doi = {10.3103/s1066530726700080}
}
Kostenlos starten →