Nonparametric geometric outlier detection

DOI10.1111/SJOS.12399MaRDI QIDQ3299036zbMATH OpenOpenAlexWikidataFDO

Authors Matias Heikkilä

Publication date 17 July 2020

Published in Scandinavian Journal of Statistics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1811.05169

zbMATH Keywords

robust statisticsDelaunay triangulationVoronoi diagramnonparametric geometric outlier detection

Mathematics Subject Classification ID

Nonparametric robustness (62G35) Statistics of extreme values; tail inference (62G32) Statistics on manifolds (62R30) Triangulating (57R05)

Abstract: Outlier detection is a major topic in robust statistics due to the high practical significance of anomalous observations. Many existing methods are, however, either parametric or cease to perform well when the data is far from linearly structured. In this paper, we propose a quantity, Delaunay outlyingness, that is a nonparametric outlyingness score applicable to data with complicated structure. The approach is based a well known triangulation of the sample, which seems to reflect the sparsity of the pointset to different directions in a useful way. In addition to appealing to heuristics, we derive results on the asymptotic behaviour of Delaunay outlyingness in the case of a sufficiently simple set of observations. Simulations and an application to financial data are also discussed.

Recommendations

• Nonparametric tests for detection of high dimensional outliers
• RDELA -- a Delaunay-triangulation-based, location and covariance estimator with high breakdown point
• Outlier detection for high-dimensional data
• Outlier detection in interval data
• Design-based estimation for geometric quantiles with application to outlier detection

Cited in

(9)

• scientific article; zbMATH DE number 3986505 (Why is no real title available?)
• Anomaly detection in the probability simplex under different geometries
• Design-based estimation for geometric quantiles with application to outlier detection
• A Geometrical–Statistical Approach to Outlier Removal for TDOA Measurements
• Nonparametric tests for detection of high dimensional outliers
• RDELA -- a Delaunay-triangulation-based, location and covariance estimator with high breakdown point
• Geometric anomaly detection in data
• A method of outlier detection based on nonparametric density estimation
• A geometric analysis of subspace clustering with outliers

This page was built for publication: Nonparametric geometric outlier detection

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3299036)