Outlier detection for high dimensional data using the Comedian approach

DOI10.1080/00949655.2011.552504zbMath1432.62164OpenAlexW1971460477MaRDI QIDQ4912049

M. R. Srinivasan, T. A. Sajesh

Publication date: 21 March 2013

Published in: Journal of Statistical Computation and Simulation (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1080/00949655.2011.552504

zbMATH Keywords

robust statisticsoutlier detectionMahalanobis distancebreakdown value

Mathematics Subject Classification ID

Estimation in multivariate analysis (62H12) Robustness and adaptive procedures (parametric inference) (62F35)

Related Items (12)

Distance-based outlier detection for high dimension, low sample size data ⋮ Robust distance measure to detect outliers for categorical data ⋮ Proposition of new alternative tests adapted to the traditional T² test ⋮ Proposition and validation of multivariate tests of independence between two groups of variables ⋮ Enhancing multivariate control charts for individual observations using ROC estimates ⋮ Geographically weighted Comedian method for spatial outlier detection ⋮ Unnamed Item ⋮ A co-median approach to detect compositional outliers ⋮ Subspace rotations for high-dimensional outlier detection ⋮ Multivariate outlier detection based on a robust Mahalanobis distance with shrinkage estimators ⋮ Robust modified classical spherical tests in the presence of outliers ⋮ Multidimensional outlier detection and robust estimation using S_n covariance

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Breakdown points of affine equivariant estimators of multivariate location and covariance matrices
• Limit theorems for the median deviation
• Robust m-estimators of multivariate location and scatter
• Finite sample breakdown points of projection based multivariate location and scatter statistics
• On MAD and comedians
• Stability of principal component analysis studied by the bootstrap method
• Robust Procedures in Multivariate Analysis I: Robust Covariance Estimation
• Transformation of non positive semidefinite correlation matrices
• Unified scheme for testing for outliers in linear models

This page was built for publication: Outlier detection for high dimensional data using the Comedian approach