An adaptive composite quantile approach to dimension reduction

DOI10.1214/14-AOS1242zbMATH Open1310.62052arXiv1408.3221MaRDI QIDQ464203FDOQ464203

Authors: Efang Kong, Yingcun Xia 

Publication date: 17 October 2014

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

Abstract: Sufficient dimension reduction [J. Amer. Statist. Assoc. 86 (1991) 316-342] has long been a prominent issue in multivariate nonparametric regression analysis. To uncover the central dimension reduction space, we propose in this paper an adaptive composite quantile approach. Compared to existing methods, (1) it requires minimal assumptions and is capable of revealing all dimension reduction directions; (2) it is robust against outliers and (3) it is structure-adaptive, thus more efficient. Asymptotic results are proved and numerical examples are provided, including a real data analysis.

Full work available at URL: https://arxiv.org/abs/1408.3221

Recommendations

• Adaptive composite quantile regressions and their asymptotic relative efficiency
• A data-adaptive hybrid method for dimension reduction
• An effective method to reduce the computational complexity of composite quantile regression
• An Adaptive Estimation of Dimension Reduction Space
• High-dimensional composite quantile regression: optimal statistical guarantees and fast algorithms
• Nonlinear dimension reduction for conditional quantiles
• An adaptive algorithm for quantile regression
• Composite quantile regression for massive datasets

zbMATH Keywords

quantile regressionsemiparametric modelssufficient dimension reductionlocal polynomial smoothing\(\mathrm{U}\)-processesBahadur approximation

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Asymptotic properties of nonparametric inference (62G20) Nonparametric robustness (62G35) Sufficient statistics and fields (62B05)

Cites Work

• A constructive approach to the estimation of dimension reduction directions
• Sliced Regression for Dimension Reduction
• Weak convergence and empirical processes. With applications to statistics
• Regression Quantiles
• Sliced Inverse Regression for Dimension Reduction
• Goodness of Fit and Related Inference Processes for Quantile Regression
• Simulation and the Asymptotics of Optimization Estimators
• An Adaptive Estimation of Dimension Reduction Space
• U-processes: Rates of convergence
• Convergence of stochastic processes
• Contour regression: a general approach to dimension reduction
• Fourier Methods for Estimating the Central Subspace and the Central Mean Subspace in Regression
• Title not available (Why is that?)
• A semiparametric approach to dimension reduction
• Dimension reduction in regressions through cumulative slicing estimation
• Quantile-adaptive model-free variable screening for high-dimensional heterogeneous data
• On average derivative quantile regression
• Kernel dimension reduction in regression
• Local Linear Quantile Regression
• Quantile smoothing splines
• MULTIVARIATE LOCAL POLYNOMIAL REGRESSION FOR TIME SERIES:UNIFORM STRONG CONSISTENCY AND RATES
• Fisher lecture: Dimension reduction in regression
• Composite quantile regression and the oracle model selection theory
• Asymptotics for kernel estimate of sliced inverse regression
• Structure adaptive approach for dimension reduction.
• Dimension reduction for conditional mean in regression
• Principal Hessian Directions for regression with measurement error
• Dimension Reduction for the Conditionalkth Moment in Regression
• Perturbation theory for linear operators.
• Successive direction extraction for estimating the central subspace in a multiple-index regres\-sion
• Dimension reduction for the conditional mean in regressions with categorical predictors
• Uniform Bahadur representation for local polynomial estimates of M-regression and its application to the additive model
• Global nonparametric estimation of conditional quantile functions and their derivatives
• Kernel and nearest-neighbor estimation of a conditional quantile
• Sufficient dimension reduction based on an ensemble of minimum average variance estimators
• Title not available (Why is that?)
• Asymptotic properties of kernel estimators based on local medians
• A Bernstein-type inequality for \(U\)-statistics and \(U\)-processes
• Title not available (Why is that?)
• Global Bahadur representation for nonparametric censored regression quantiles and its applications

Cited In (22)

• Robust dimension reduction using sliced inverse median regression
• A brief review of linear sufficient dimension reduction through optimization
• Double-slicing assisted sufficient dimension reduction for high-dimensional censored data
• Principal quantile regression for sufficient dimension reduction with heteroscedasticity
• Sparse sufficient dimension reduction with heteroscedasticity
• Quantile-slicing estimation for dimension reduction in regression
• Nonlinear interaction detection through partial dimension reduction with missing response data
• Transformed central quantile subspace
• Model-free feature screening via a modified composite quantile correlation
• Central quantile subspace
• A structured covariance ensemble for sufficient dimension reduction
• Advance of the sufficient dimension reduction
• Projection expectile regression for sufficient dimension reduction
• Quantile based dimension reduction in censored regression
• Uniform Bahadur representation for nonparametric censored quantile regression: a redistribution-of-mass approach
• Composite quantile regression for ultra-high dimensional semiparametric model averaging
• Quantile Martingale Difference Divergence for Dimension Reduction
• Sufficient dimension reduction for conditional quantiles with alternative types of data
• Dimension reduction via local rank regression
• Penalized averaging of parametric and non-parametric quantile forecasts
• Weighted composite quantile regression for single index model with missing covariates at random
• Nonlinear dimension reduction for conditional quantiles

This page was built for publication: An adaptive composite quantile approach to dimension reduction

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q464203)