Transformed sufficient dimension reduction

DOI10.1093/BIOMET/ASU037MaRDI QIDQ2934763zbMATH OpenOpenAlexFDO

Authors Tao Wang, Xu Guo, Li-Xing Zhu, Pei-Rong Xu

Publication date 22 December 2014

Published in Biometrika (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1401.0267

zbMATH Keywords

minimum average variance estimationmonotone smoothing splinepredictor transformationprobability integral transformationsliced inverse regression

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08)

Abstract: A novel general framework is proposed in this paper for dimension reduction in regression to fill the gap between linear and fully nonlinear dimension reduction. The main idea is to transform first each of the raw predictors monotonically, and then search for a low-dimensional projection in the space defined by the transformed variables. Both user-specified and data-driven transformations are suggested. In each case, the methodology is discussed first in a general manner, and a representative method, as an example, is then proposed and evaluated by simulation. The proposed methods are applied to a real data set for illustration.

Recommendations

• Flexible dimension reduction in regression
• Sufficient dimension reduction and prediction in regression
• Dimension reduction for nonelliptically distributed predictors
• Kernel dimension reduction in regression
• Optimal transformation: a new approach for covering the central subspace

Cited in

(13)

• Transformation-based estimation
• Canonical kernel dimension reduction
• Principal minimax support vector machine for sufficient dimension reduction with contaminated data
• Optimal transformation: a new approach for covering the central subspace
• On permutation tests for predictor contribution in sufficient dimension reduction
• scientific article; zbMATH DE number 5968945 (Why is no real title available?)
• A two-stage dimension-reduction method for transformed responses and its applications
• The dimension reduction method based on data transformations
• Transformed central quantile subspace
• Model-Free Variable Selection With Matrix-Valued Predictors
• Transformed partial least squares for multivariate data
• Dimension reduction techniques for conditional expectiles
• Group sparse sufficient dimension reduction: a model-free group variable selection method

This page was built for publication: Transformed sufficient dimension reduction

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2934763)