Zonoid trimming for multivariate distributions

From MaRDI portal
Publication:1374221

DOI10.1214/aos/1069362382zbMath0881.62059OpenAlexW2088146874MaRDI QIDQ1374221

Karl C. Mosler, Gleb A. Koshevoy

Publication date: 2 December 1997

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1214/aos/1069362382




Related Items

Convex bodies generated by sublinear expectations of random vectorsOn maximum depth classifiers: depth distribution approachRR-plot: a descriptive tool for regression observationsComputation of projection regression depth and its induced medianApproximate computation of projection depthsConvergence of depth contours for multivariate datasetsA martingale bound for the entropy associated with a trimmed filtration on \(\mathbb{R}^d\)Lift zonoid and barycentric representation on a Banach space with a cylinder measureExact computation of the halfspace depthChoosing among notions of multivariate depth statisticsSome multivariate goodness of fit tests based on data depthDepth-weighted Bayes classificationA notion of depth for sparse functional dataLift zonoid order and functional inequalitiesRobust estimation of location and scatter by pruning the minimum spanning treeClassifying real-world data with the \(DD\alpha\)-procedureLevel sets of depth measures in abstract spacesDepth and outliers for samples of sets and random sets distributionsMultivariate Kruskal_Wallis tests based on principal component score and latent source of independent component analysisTesting for diagonal symmetry based on center-outward rankingDepth level set estimation and associated risk measuresThe zonoid region parameter depthTrimmed regions induced by parameters of a probabilityFast implementation of the Tukey depthWeighted-mean regions of a probability distributionOn the uniform consistency of the zonoid depthAffine invariant integrated rank-weighted statistical depth: properties and finite sample analysisWeighted-mean trimming of multivariate dataUnnamed ItemDirectional bivariate quantiles: a robust approach based on the cumulative distribution functionA scatter matrix estimate based on the zonotopeGeneralized and robustified empirical depths for multivariate dataOn Combinatorial Depth MeasuresComputing zonoid trimmed regions of bivariate data setsAn introduction to copula-based bivariate reliability ConceptsMultivariate Lorenz dominance based on zonoidsNonparametric Imputation by Data DepthGeometric disintegration and star-shaped distributionsComputing zonoid trimmed regions of dimension \(d>2\)Halfspace depth and floating bodyThe expected convex hull trimmed regions of a sampleFast nonparametric classification based on data depthDepth-based classification for distributions with nonconvex supportA new concept of quantiles for directional data and the angular Mahalanobis depthAffine invariant depth-based tests for the multivariate one-sample location problemExpectile depth: theory and computation for bivariate datasetsOn general notions of depth for regressionConsistency of the \(\alpha \)-trimming of a probability. Applications to central regionsMultivariate risks and depth-trimmed regionsDirichlet depths for point processControl charts based on parameter depthsThe flood algorithm -- a multivariate, self-organizing-map-based, robust location and covariance estimatorQuantile curves and dependence structure for bivariate distributionsIntrinsic Data Depth for Hermitian Positive Definite MatricesSimultaneous monitoring of origin and scale in left-bounded processes via depthConvex and star-shaped sets associated with multivariate stable distributions. I: Moments and densitiesHalfspace depth and regression depth characterize the empirical distributionGeneral notions of statistical depth function.Commentary on ``From unidimensional to multidimensional inequality: a reviewFrom Depth to Local Depth: A Focus on CentralityIntegral trimmed regionsNonparametrically consistent depth-based classifiersComputing halfspace depth contours based on the idea of a circular sequenceCombining dependent tests based on data depth with applications to the two-sample problem for data of arbitrary types