On weighted multivariate sign functions

DOI10.1016/J.JMVA.2022.105013MaRDI QIDQ2146460zbMATH OpenOpenAlexWikidataFDO

Authors Subhabrata Majumdar, Snigdhansu Chatterjee

Publication date 16 June 2022

Published in Journal of Multivariate Analysis (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1905.02700

zbMATH Keywords

data depthmultivariate signoutlier detectionprincipal component analysissufficient dimension reduction

Mathematics Subject Classification ID

Multivariate distribution of statistics (62H10) Factor analysis and principal components; correspondence analysis (62H25)

Abstract: Multivariate sign functions are often used for robust estimation and inference. We propose using data dependent weights in association with such functions. The proposed weighted sign functions retain desirable robustness properties, while significantly improving efficiency in estimation and inference compared to unweighted multivariate sign-based methods. Using weighted signs, we demonstrate methods of robust location estimation and robust principal component analysis. We extend the scope of using robust multivariate methods to include robust sufficient dimension reduction and functional outlier detection. Several numerical studies and real data applications demonstrate the efficacy of the proposed methodology.

Recommendations

• The minimum weighted covariance determinant estimator
• Weighted likelihood estimation of multivariate location and scatter
• On the Stahel-Donoho estimator and depth-weighted means of multivariate data.
• Robust estimation of multivariate regression model
• On the weighted multivariate Wilcoxon rank regression estimate

Cites work

• \(M\)-estimation, convexity and quantiles
• S-estimator for functional principal component analysis
• A distribution-free M-estimator of multivariate scatter
• A generalized spatial sign covariance matrix
• A high-dimensional nonparametric multivariate test for mean vector
• A Multivariate Signed-Rank Test for the One-Sample Location Problem
• A weighted spatial median for clustered data
• Asymptotics for \(M\)-estimators defined by convex minimization
• Concavity and estimation
• Depth weighted scatter estimators
• Envelope models for parsimonious and efficient multivariate linear regression
• Foundations for envelope models and methods
• General notions of statistical depth function.
• Generalized bootstrap for estimating equations
• Geometric median and robust estimation in Banach spaces
• scientific article; zbMATH DE number 3642533 (Why is no real title available?)
• scientific article; zbMATH DE number 3954047 (Why is no real title available?)
• scientific article; zbMATH DE number 45785 (Why is no real title available?)
• scientific article; zbMATH DE number 5200028 (Why is no real title available?)
• Multivariate analysis by data depth: Descriptive statistics, graphics and inference. (With discussions and rejoinder)
• Multivariate nonparametric methods with R. An approach based on spatial signs and ranks.
• Multivariate spatial sign and rank methods
• Nonparametric analysis of clustered multivariate data
• Nonparametrics and robustness in modern statistical inference and time series analysis: A Festschrift in honor of Professor Jana Jurečková
• Note on the median of a multivariate distribution
• On a Geometric Notion of Quantiles for Multivariate Data
• On principal angles between subspaces in \(\mathbb{R}^n\)
• On the limiting distributions of multivariate depth-based rank sum statistics and related tests
• On the multivariate spatial median for clustered data
• Online estimation of the geometric median in Hilbert spaces: nonasymptotic confidence balls
• Optimal rank-based testing for principal components
• Principal component analysis based on robust estimators of the covariance or correlation matrix: influence functions and efficiencies
• Projection-based depth functions and associated medians
• Robust functional principal components: a projection-pursuit approach
• Robust principal component analysis for functional data. (With comments)
• Robust Statistics
• Robustifying principal component analysis with spatial sign vectors
• Sign and rank covariance matrices
• Some robust estimates of principal components
• Sufficient dimension reduction and prediction in regression
• The \(k\)-step spatial sign covariance matrix
• The asymptotic inadmissibility of the spatial sign covariance matrix for elliptically symmetric distributions
• The spatial distribution in infinite dimensional spaces and related quantiles and depths
• The spatial sign covariance matrix with unknown location
• The spatial sign covariance operator: asymptotic results and applications

Cited in

(1)

• A value function that explains the magnitude and sign effects

Describes a project that uses

Uses Software

• MNM
• R
• fda.usc
• ddalpha
• robustbase
• ROBPCA

This page was built for publication: On weighted multivariate sign functions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2146460)