Quantile-adaptive model-free variable screening for high-dimensional heterogeneous data

Abstract

We introduce a quantile-adaptive framework for nonlinear variable screening with high-dimensional heterogeneous data. This framework has two distinctive features: (1) it allows the set of active variables to vary across quantiles, thus making it more flexible to accommodate heterogeneity; (2) it is model-free and avoids the difficult task of specifying the form of a statistical model in a high dimensional space. Our nonlinear independence screening procedure employs spline approximations to model the marginal effects at a quantile level of interest. Under appropriate conditions on the quantile functions without requiring the existence of any moments, the new procedure is shown to enjoy the sure screening property in ultra-high dimensions. Furthermore, the quantile-adaptive framework can naturally handle censored data arising in survival analysis. We prove that the sure screening property remains valid when the response variable is subject to random right censoring. Numerical studies confirm the fine performance of the proposed method for various semiparametric models and its effectiveness to extract quantile-specific information from heteroscedastic data.

Published in at http://dx.doi.org/10.1214/13-AOS1087 the Annals of Statistics (http://www.imstat.org/aos/) by the Institute of Mathematical Statistics (http://www.imstat.org)

References in corpus (2)

• Asymptotics for minimisers of convex processes
• Ultrahigh dimensional variable selection: beyond the linear model

Cited by in corpus (18)

• Partially linear additive quantile regression in ultra-high dimension
• The fused Kolmogorov filter: A nonparametric model-free screening method
• Model-free Feature Screening and FDR Control with Knockoff Features
• High-Dimensional Survival Analysis: Methods and Applications
• An adaptive composite quantile approach to dimension reduction
• Adaptive LASSO model selection in a multiphase quantile regression
• Interaction Pursuit with Feature Screening and Selection
• Nonparametric Screening under Conditional Strictly Convex Loss for Ultrahigh Dimensional Sparse Data
• Semiparametric Expectile Regression for High-dimensional Heavy-tailed and Heterogeneous Data
• Copula-based Partial Correlation Screening: a Joint and Robust Approach
• Bayesian iterative screening in ultra-high dimensional linear regressions
• Inference for High Dimensional Censored Quantile Regression
• Model-Free Conditional Feature Screening with Exposure Variables
• Greedy Forward Regression for Variable Screening
• Fused Mean-variance Filter for Feature Screening
• Nearly Semiparametric Efficient Estimation of Quantile Regression
• Trace Pursuit: A General Framework for Model-Free Variable Selection
• Covariance-Insured Screening