Multivariate quantiles and multiple-output regression quantiles: from L₁ optimization to halfspace depth
From MaRDI portal
Publication:2380085
DOI10.1214/09-AOS723zbMATH Open1183.62088arXiv1002.4486OpenAlexW1991452110MaRDI QIDQ2380085FDOQ2380085
Authors: Marc Hallin, Davy Paindaveine, Miroslav Šiman 
Publication date: 24 March 2010
Published in: The Annals of Statistics (Search for Journal in Brave)
Abstract: A new multivariate concept of quantile, based on a directional version of Koenker and Bassett's traditional regression quantiles, is introduced for multivariate location and multiple-output regression problems. In their empirical version, those quantiles can be computed efficiently via linear programming techniques. Consistency, Bahadur representation and asymptotic normality results are established. Most importantly, the contours generated by those quantiles are shown to coincide with the classical halfspace depth contours associated with the name of Tukey. This relation does not only allow for efficient depth contour computations by means of parametric linear programming, but also for transferring from the quantile to the depth universe such asymptotic results as Bahadur representations. Finally, linear programming duality opens the way to promising developments in depth-related multivariate rank-based inference.
Full work available at URL: https://arxiv.org/abs/1002.4486
Recommendations
Asymptotic properties of nonparametric inference (62G20) Linear regression; mixed models (62J05) Characterization and structure theory for multivariate probability distributions; copulas (62H05) Linear programming (90C05) Applications of mathematical programming (90C90) Graphical methods in statistics (62A09)
Cites Work
- Algorithm AS 307: Bivariate Location Depth
- Regression rank scores and regression quantiles
- Regression Quantiles
- Quantile regression.
- Breakdown properties of location estimates based on halfspace depth and projected outlyingness
- \(M\)-estimation, convexity and quantiles
- On a Geometric Notion of Quantiles for Multivariate Data
- Concavity and estimation
- Multivariate analysis by data depth: Descriptive statistics, graphics and inference. (With discussions and rejoinder)
- General notions of statistical depth function.
- M-quantiles
- Regression Depth
- Equivariance and invariance properties of multivariate quantile and related functions, and the role of standardisation
- Title not available (Why is that?)
- Power Transformations to Induce Normality and their Applications
- Structural properties and convergence results for contours of sample statistical depth functions.
- On depth and deep points: A calculus.
- Quantile tomography: using quantiles with multivariate data
- Computing multiple-output regression quantile regions
- The depth function of a population distribution.
- On directional multiple-output quantile regression
- An Approach to Multivariate Covariate-Dependent Quantile Contours With Application to Bivariate Conditional Growth Charts
- Quantile functions for multivariate analysis: approaches and applications
- Characterizing angular symmetry and regression symmetry.
- On multivariate quantile regression
- Asymptotics for \(M\)-estimators defined by convex minimization
- Halfspace depth and regression depth characterize the empirical distribution
- Note on the spatial quantile of a random vector
- Title not available (Why is that?)
- On affine equivariant multivariate quantiles
- On Certain Bivariate Sign Tests and Medians
- On spatial quantiles
- A note on multivariate \(M\)-quantiles
- Fast implementation of depth contours using topological sweep
Cited In (95)
- On elliptical quantiles in the quantile regression setup
- Simplified simplicial depth for regression and autoregressive growth processes
- Computing halfspace depth contours based on the idea of a circular sequence
- Computing multiple-output regression quantile regions
- A Bayesian quantile regression approach to multivariate semi-continuous longitudinal data
- Computing halfspace depth and regression depth
- On directional multiple-output quantile regression
- Elliptical multiple-output quantile regression and convex optimization
- A joint quantile regression model for multiple longitudinal outcomes
- Statistical data analysis based on the \(L_1\)-norm and related methods. With the technical assistance of Giuseppe Melfi. Papers of the 4th international conference on statistical analysis on the \(L_1\)-norm and related methods, Neuchâtel, Switzerland, August 4--9, 2002
- Exact computation of the halfspace depth
- Vector-on-function quantile regression for stationary ergodic processes
- Finite sample breakdown point of Tukey's halfspace median
- Concentration of the empirical level sets of Tukey's halfspace depth
- Multivariate functional halfspace depth
- Halfspace depths for scatter, concentration and shape matrices
- Cone distribution functions and quantiles for multivariate random variables
- A new concept of quantiles for directional data and the angular Mahalanobis depth
- Multivariate geometric expectiles
- Vector quantile regression: an optimal transport approach
- Distribution and quantile functions, ranks and signs in dimension \(d\): a measure transportation approach
- On general notions of depth for regression
- Reconstruction of atomic measures from their halfspace depth
- Testing multivariate economic restrictions using quantiles: the example of Slutsky negative semidefiniteness
- Multivariate and functional classification using depth and distance
- On multivariate quantiles under partial orders
- Bayesian regularized quantile structural equation models
- General jackknife empirical likelihood and its applications
- Joint estimation of conditional quantiles in multivariate linear regression models with an application to financial distress
- Fast Computation of Tukey Trimmed Regions and Median in Dimension p > 2
- Multivariate Hill Estimators
- On the estimation of extreme directional multivariate quantiles
- On generalized elliptical quantiles in the nonlinear quantile regression setup
- Discussion of ``Local quantile regression
- Equivariance and invariance properties of multivariate quantile and related functions, and the role of standardisation
- Local bilinear multiple-output quantile/depth regression
- ADMM for Penalized Quantile Regression in Big Data
- Reduced rank regression with possibly non-smooth criterion functions: an empirical likelihood approach
- Testing axial symmetry by means of directional regression quantiles
- Testing symmetry around a subspace
- A note on multivariate \(M\)-quantiles
- Computing multiple-output regression quantile regions from projection quantiles
- Bridging centrality and extremity: refining empirical data depth using extreme value statistics
- On multivariate quantile regression
- From Depth to Local Depth: A Focus on Centrality
- A directional multivariate value at risk
- A Bayesian Approach to Multiple-Output Quantile Regression
- Spatial quantiles on the hypersphere
- Bayesian quantile regression using the skew exponential power distribution
- Regression Depth
- Multidimensional medians and uniqueness
- A weighted localization of halfspace depth and its properties
- Linear quantile regression models for longitudinal experiments: an overview
- Multivariate \(\rho \)-quantiles: a spatial approach
- A new approach for the computation of halfspace depth in high dimensions
- Fast implementation of the Tukey depth
- Multiple-output quantile regression through optimal quantization
- Depth for curve data and applications
- Computing projection depth and its associated estimators
- Multivariate functional outlier detection
- On multivariate quantile regression analysis
- Quantiles for finite and infinite dimensional data
- On weighted and locally polynomial directional quantile regression
- Fast optimization methods for high-dimensional row-sparse multivariate quantile linear regression
- Directional bivariate quantiles: a robust approach based on the cumulative distribution function
- On exact computation of some statistics based on projection pursuit in a general regression context
- Precision index in the multivariate context
- Highly robust training of regularized radial basis function networks.
- Modeling conditional reference regions: application to glycemic markers
- Bivariate Functional Quantile Envelopes With Application to Radiosonde Wind Data
- Testing axial symmetry by means of integrated rank scores
- Multiscale Quantile Segmentation
- Marginal M-quantile regression for multivariate dependent data
- Multivariate quantile impulse response functions
- Discussion
- The sparse method of simulated quantiles: An application to portfolio optimization
- Regularity of center-outward distribution functions in non-convex domains
- Estimating impulse-response functions for macroeconomic models using directional quantiles
- Multivariate process capability indices: a directional approach
- Empirical Dynamic Quantiles for Visualization of High-Dimensional Time Series
- Choosing among notions of multivariate depth statistics
- Reduced form vector directional quantiles
- On easily interpretable multivariate reference regions of rectangular shape
- Combining dependent tests based on data depth with applications to the two-sample problem for data of arbitrary types
- Gibbs posterior inference on multivariate quantiles
- Adaptiveness of the empirical distribution of residuals in semi-parametric conditional location scale models
- Flexible quantile contour estimation for multivariate functional data: beyond convexity
- Deterministic computation of quantiles in a Lipschitz framework
- Noncrossing structured additive multiple-output Bayesian quantile regression models
- Parallel computation of bivariate point data depths and display of intrinsic depth segments
- Flexible integrated functional depths
- Directional multivariate extremes in environmental phenomena
- Vector quantile regression beyond the specified case
- Multiple-output quantile regression neural network
- Multivariate ranks and quantiles using optimal transport: consistency, rates and nonparametric testing
Uses Software
This page was built for publication: Multivariate quantiles and multiple-output regression quantiles: from \(L_{1}\) optimization to halfspace depth
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2380085)
