High-breakdown robust multivariate methods

DOI10.1214/088342307000000087zbMATH Open1327.62328arXiv0808.0657OpenAlexW3100039232MaRDI QIDQ900488FDOQ900488

Mia Hubert, Peter Rousseeuw, Stefan Van Aelst

Publication date: 22 December 2015

Published in: Statistical Science (Search for Journal in Brave)

Abstract: When applying a statistical method in practice it often occurs that some observations deviate from the usual assumptions. However, many classical methods are sensitive to outliers. The goal of robust statistics is to develop methods that are robust against the possibility that one or several unannounced outliers may occur anywhere in the data. These methods then allow to detect outlying observations by their residuals from a robust fit. We focus on high-breakdown methods, which can deal with a substantial fraction of outliers in the data. We give an overview of recent high-breakdown robust methods for multivariate settings such as covariance estimation, multiple and multivariate regression, discriminant analysis, principal components and multivariate calibration.

Full work available at URL: https://arxiv.org/abs/0808.0657

Recommendations

• Multivariate outlier detection with high-breakdown estimators
• scientific article; zbMATH DE number 897986
• Robust estimation of multivariate location and shape
• Robust tools for the imperfect world
• Robust multivariate analysis

zbMATH Keywords

outliersprincipal componentspartial least squaresregressionbreakdown valuerobustnessinfluence functionmultivariate statistics

Mathematics Subject Classification ID

Linear regression; mixed models (62J05) Characterization and structure theory for multivariate probability distributions; copulas (62H05)

Cites Work

• Breakdown in Nonlinear Regression
• Robust estimation for the multivariate linear model based on a \(\tau\)-scale
• Robustness of deepest regression
• Robust PCR and robust PLSR: a comparative study
• Bias-robust estimates of regression based on projections
• Functional stability of one-step GM-estimators in approximately linear regression
• Multivariate τ-Estimators for Location and Scatter
• Outlier robust analysis of long-run marketing effects for weekly scanning data
• An efficient Fréchet differentiable high breakdown multivariate location and dispersion estimator
• Bias robustness of three median-based regression estimates.
• Robust Bounded-Influence Tests in Linear Models
• Title not available (Why is that?)
• Bounded Influence and High Breakdown Point Testing Procedures in Linear Models
• A Class of Locally and Globally Robust Regression Estimates
• Nonparametric notions of multivariate scatter measure and more scattered based on statistical depth functions
• Finding Groups in Data
• Title not available (Why is that?)
• Robust regression: Asymptotics, conjectures and Monte Carlo
• Inconsistency of Resampling Algorithms for High-Breakdown Regression Estimators and a New Algorithm
• The Masking Breakdown Point of Multivariate Outlier Identification Rules
• Some Theorems on Quadratic Forms Applied in the Study of Analysis of Variance Problems, I. Effect of Inequality of Variance in the One-Way Classification
• Robust Statistics
• Outlier detection in the multiple cluster setting using the minimum covariance determinant estimator
• Asymptotic behaviour of S-estimates of multivariate location parameters and dispersion matrices
• Breakdown properties of location estimates based on halfspace depth and projected outlyingness
• Robust m-estimators of multivariate location and scatter
• Bias-robust estimators of multivariate scatter based on projections
• Robust principal component analysis for functional data. (With comments)
• Asymptotics for the minimum covariance determinant estimator
• Finite sample breakdown points of projection based multivariate location and scatter statistics
• Trimmed \(k\)-means: An attempt to robustify quantizers
• Asymptotics of reweighted estimators of multivariate location and scatter
• Robustness properties of \(S\)-estimators of multivariate location and shape in high dimension
• Constrained \(M\)-estimation for multivariate location and scatter
• On the uniqueness of \(S\)-functionals and \(M\)-functionals under nonelliptical distributions.
• Robust factor analysis.
• Influence function and efficiency of the minimum covariance determinant scatter matrix estimator
• High breakdown estimation for multiple populations with applications to discriminant analysis
• The multivariate least-trimmed squares estimator
• Least Median of Squares Regression
• Title not available (Why is that?)
• Projection-Pursuit Approach to Robust Dispersion Matrices and Principal Components: Primary Theory and Monte Carlo
• Title not available (Why is that?)
• Robust Procedures in Multivariate Analysis I: Robust Covariance Estimation
• Robust regression using repeated medians
• Alternatives to the Median Absolute Deviation
• Computable Robust Estimation of Multivariate Location and Shape in High Dimension Using Compound Estimators
• Identification of Outliers in Multivariate Data
• High-Breakdown Linear Discriminant Analysis
• Principal component analysis based on robust estimators of the covariance or correlation matrix: influence functions and efficiencies
• Robust linear discriminant analysis using S-estimators
• Title not available (Why is that?)
• A Projection Pursuit Algorithm for Exploratory Data Analysis
• The Behavior of the Stahel-Donoho Robust Multivariate Estimator
• Robust Statistics
• High breakdown estimators for principal components: the projection-pursuit approach revis\-ited
• Robust Estimates of Location: Survey and Advances
• Principal Components Analysis Based on Multivariate MM Estimators With Fast and Robust Bootstrap
• High breakdown-point and high efficiency robust estimates for regression
• Breakdown points of affine equivariant estimators of multivariate location and covariance matrices
• Small sample corrections for LTS and MCD
• A robust Hotelling test
• On the relation between S-estimators and M-estimators of multivariate location and covariance
• Fast and robust discriminant analysis
• Influence functionals for time series (with discussion)
• Multivariate analysis by data depth: Descriptive statistics, graphics and inference. (With discussions and rejoinder)
• General notions of statistical depth function.
• Title not available (Why is that?)
• Regression Depth
• Projection pursuit
• Breakdown points of trimmed likelihood estimators and related estimators in generalized linear models.
• Breakdown and groups. (With discussions and rejoinder)
• Title not available (Why is that?)
• Robust Inference for Generalized Linear Models
• Nonparametric Estimate of Regression Coefficients
• Weighted Likelihood Equations with Bootstrap Root Search
• High-Breakdown Inference for Mixed Linear Models
• Title not available (Why is that?)
• The deepest regression method
• Maximum bias curves for robust regression with non-elliptical regressors
• On depth and deep points: A calculus.
• Title not available (Why is that?)
• Robust estimates for arch processes
• Breakdown points of t-type regression estimators
• Outlier Robust Model Selection in Linear Regression
• Min-max bias robust regression
• Bootstrapping robust estimates of regression
• Robust estimation in the errors-in-variables model
• On One-Step GM Estimates and Stability of Inferences in Linear Regression
• A Robust Version of Mallows's C p
• Robust Linear Model Selection by Cross-Validation
• High Breakdown-Point Estimates of Regression by Means of the Minimization of an Efficient Scale
• L-Estimation for Linear Models
• Rank-Based Estimates in the Linear Model with High Breakdown Point
• Conditionally Unbiased Bounded-Influence Estimation in General Regression Models, with Applications to Generalized Linear Models
• The asymptotics of Rousseeuw's minimum volume ellipsoid estimator
• Lower bounds for contamination bias: Globally minimax versus locally linear estimation
• A Bounded Influence, High Breakdown, Efficient Regression Estimator
• Title not available (Why is that?)
• Multivariate regression \(S\)-estimators for robust estimation and inference
• Title not available (Why is that?)
• Robustness against separation and outliers in logistic regression
• Title not available (Why is that?)
• On the Stahel-Donoho estimator and depth-weighted means of multivariate data.
• Robust regression with both continuous and binary regressors
• Robust regression with both continuous and categorical predictors
• Asymptotic distributions of principal components based on robust dispersions
• Asymptotic behavior of general M-estimates for regression and scale with random carriers
• Bias robust estimation in orthogonal regression
• Estimators of the multiple correlation coefficient: local robustness and confidence intervals
• Influence functions and outlier detection under the common principal components model: A robust approach
• Asymptotic distributions of the maximal depth estimators for regression and multivariate location
• Efficient Bounded-Influence Regression Estimation
• Generalized S-Estimators
• Computation of High Breakdown Nonlinear Regression Parameters

Cited In (78)

• Robust estimation of location and scatter by pruning the minimum spanning tree
• Robust modifications of U-statistics and applications to covariance estimation problems
• Robust AIC with high breakdown scale estimate
• Robust estimation of precision matrices under cellwise contamination
• Robust principal component analysis via ES-algorithm
• New challenges in covariance estimation: multiple structures and coarse quantization
• Snipping for robust \(k\)-means clustering under component-wise contamination
• Assessing robustness of classification using an angular breakdown point
• Outlier detection in interval data
• Robust surface estimation in multi-response multistage statistical optimization problems
• Detecting outliers and influential points: an indirect classical Mahalanobis distance-based method
• Fusing data depth with complex networks: community detection with prior information
• Outlier detection in non-elliptical data by kernel MRCD
• Robust distances for outlier-free goodness-of-fit testing
• Fast approximate \(L_\infty\) minimization: speeding up robust regression
• Asymptotic expansion of the minimum covariance determinant estimators
• Least quantile regression via modern optimization
• Outlier-free merging of homogeneous groups of pre-classified observations under contamination
• Sub-Gaussian estimators of the mean of a random matrix with heavy-tailed entries
• Reliable Robust Regression Diagnostics
• Weighted likelihood estimation of multivariate location and scatter
• Multivariate outlier detection based on a robust Mahalanobis distance with shrinkage estimators
• Fast robust estimation of prediction error based on resampling
• Matrix strategies for computing the least trimmed squares estimation of the general linear and SUR models
• Projection-pursuit approach to robust linear discriminant analysis
• Tyler's and Maronna's M-estimators: non-asymptotic concentration results
• Diagnostic robust generalized potential based on index set equality (DRGP (ISE)) for the identification of high leverage points in linear model
• Depth-based classification for relational data with multiple attributes
• Fitting parabolas in noisy images
• Correcting outliers in GARCH models: a weighted forward approach
• Implicitly weighted methods in robust image analysis
• RDELA -- a Delaunay-triangulation-based, location and covariance estimator with high breakdown point
• The flood algorithm -- a multivariate, self-organizing-map-based, robust location and covariance estimator
• Robust estimation for the Cox regression model based on trimming
• Evolutionary optimization for robust epipolar-geometry estimation and outlier detection
• Some notes on robust sure independence screening
• The forward search: theory and data analysis
• Strong consistency and robustness of the forward search estimator of multivariate location and scatter
• Robust tools for the imperfect world
• Robust statistic for the one-way MANOVA
• The minimum regularized covariance determinant estimator
• Robust and sparse multigroup classification by the optimal scoring approach
• Bounded influence nonlinear signed-rank regression
• Inference for robust canonical variate analysis
• Robust Bayesian seemingly unrelated regression model
• Fast estimation of the median covariation matrix with application to online robust principal components analysis
• Characterization of the equivalence of robustification and regularization in linear and matrix regression
• Small area estimation based on M-quantile models in presence of outliers in auxiliary variables
• The power of monitoring: how to make the most of a contaminated multivariate sample
• Robust generalized confidence intervals
• Central limit theorem and influence function for the MCD estimators at general multivariate distributions
• On Characterizations and Tests of Benford’s Law
• Geometric median and robust estimation in Banach spaces
• A plug-in approach to sparse and robust principal component analysis
• Wild adaptive trimming for robust estimation and cluster analysis
• On consistency factors and efficiency of robust \(S\)-estimators
• User-friendly covariance estimation for heavy-tailed distributions
• Error rates for multivariate outlier detection
• Robust Estimation of Multi-response Surfaces Considering Correlation Structure
• Goodness-of-Fit Testing for the Newcomb-Benford Law With Application to the Detection of Customs Fraud
• A high breakdown, high efficiency and bounded influence modified GM estimator based on support vector regression
• Adaptive subsample estimation for multivariate normal distributions
• Title not available (Why is that?)
• Quantile Inverse Optimization: Improving Stability in Inverse Linear Programming
• Regression Neural Networks with a Highly Robust Loss Function
• Quantitative robustness of instance ranking problems
• Robust estimation of covariance matrices: adversarial contamination and beyond
• Robust Multivariate Lasso Regression with Covariance Estimation
• Influence Analysis on Discriminant Coordinates
• Fast Robust Location and Scatter Estimation: A Depth-based Method
• Title not available (Why is that?)
• Consistency factor for the MCD estimator at the Student-\(t\) distribution
• Non-asymptotic analysis and inference for an outlyingness induced winsorized mean
• On Huber's contaminated model
• Robust sparse principal component analysis: situation of full sparseness
• Robust Principal Component Functional Logistic Regression
• Minimum covariance determinant and extensions
• A robust sparse linear approach for contaminated data

Uses Software

• robustbase
• LIBRA
• ROBPCA

This page was built for publication: High-breakdown robust multivariate methods

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q900488)