Leave-One-Out Kernel Density Estimates for Outlier Detection

DOI10.1080/10618600.2021.2000425OpenAlexW3214399988MaRDI QIDQ5084456

Rob Hyndman, Sevvandi Kandanaarachchi

Publication date: 24 June 2022

Published in: Journal of Computational and Graphical Statistics (Search for Journal in Brave)

Full work available at URL: https://www.monash.edu/business/ebs/research/publications/ebs/wp02-2021.pdf

zbMATH Keywords

extreme value theorytopological data analysisgeneralized Pareto distributionpersistent homologyanomaly detectionpeak over thresholds

Mathematics Subject Classification ID

Statistics (62-XX)

Related Items (1)

lookout

Uses Software

• ismev
• evd
• TDAstats
• SiZer
• outselect

Cites Work

• Unnamed Item
• Anomaly Detection in Streaming Nonstationary Temporal Data
• On the local behavior of spaces of natural images
• Statistical inference using extreme order statistics
• On normalization and algorithm selection for unsupervised outlier detection
• Sliding windows and persistence: an application of topological methods to signal analysis
• Additive Outlier Detection Via Extreme-Value Theory
• Topology and data
• SiZer for Exploration of Structures in Curves
• Anomaly Detection in High-Dimensional Data
• Multivariate Density Estimation
• Barcodes: The persistent topology of data
• An introduction to statistical modeling of extreme values

This page was built for publication: Leave-One-Out Kernel Density Estimates for Outlier Detection