Successive direction extraction for estimating the central subspace in a multiple-index regression

Xiangrong Yin, Bing Li, R. Dennis Cook

Research output: Contribution to journalArticle

89 Citations (Scopus)

Abstract

In this paper we propose a dimension reduction method for estimating the directions in a multiple-index regression based on information extraction. This extends the recent work of Yin and Cook [X. Yin, R.D. Cook, Direction estimation in single-index regression, Biometrika 92 (2005) 371-384] who introduced the method and used it to estimate the direction in a single-index regression. While a formal extension seems conceptually straightforward, there is a fundamentally new aspect of our extension: We are able to show that, under the assumption of elliptical predictors, the estimation of multiple-index regressions can be decomposed into successive single-index estimation problems. This significantly reduces the computational complexity, because the nonparametric procedure involves only a one-dimensional search at each stage. In addition, we developed a permutation test to assist in estimating the dimension of a multiple-index regression.

Original languageEnglish (US)
Pages (from-to)1733-1757
Number of pages25
JournalJournal of Multivariate Analysis
Volume99
Issue number8
DOIs
StatePublished - Sep 1 2008

Fingerprint

Central Subspace
Regression
Computational complexity
Permutation Test
Information Extraction
Dimension Reduction
Reduction Method
Predictors
Computational Complexity
Estimate

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Numerical Analysis
  • Statistics, Probability and Uncertainty

Cite this

@article{1ddbfbf4190844a6992c52871119a22b,
title = "Successive direction extraction for estimating the central subspace in a multiple-index regression",
abstract = "In this paper we propose a dimension reduction method for estimating the directions in a multiple-index regression based on information extraction. This extends the recent work of Yin and Cook [X. Yin, R.D. Cook, Direction estimation in single-index regression, Biometrika 92 (2005) 371-384] who introduced the method and used it to estimate the direction in a single-index regression. While a formal extension seems conceptually straightforward, there is a fundamentally new aspect of our extension: We are able to show that, under the assumption of elliptical predictors, the estimation of multiple-index regressions can be decomposed into successive single-index estimation problems. This significantly reduces the computational complexity, because the nonparametric procedure involves only a one-dimensional search at each stage. In addition, we developed a permutation test to assist in estimating the dimension of a multiple-index regression.",
author = "Xiangrong Yin and Bing Li and Cook, {R. Dennis}",
year = "2008",
month = "9",
day = "1",
doi = "10.1016/j.jmva.2008.01.006",
language = "English (US)",
volume = "99",
pages = "1733--1757",
journal = "Journal of Multivariate Analysis",
issn = "0047-259X",
publisher = "Academic Press Inc.",
number = "8",

}

Successive direction extraction for estimating the central subspace in a multiple-index regression. / Yin, Xiangrong; Li, Bing; Cook, R. Dennis.

In: Journal of Multivariate Analysis, Vol. 99, No. 8, 01.09.2008, p. 1733-1757.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Successive direction extraction for estimating the central subspace in a multiple-index regression

AU - Yin, Xiangrong

AU - Li, Bing

AU - Cook, R. Dennis

PY - 2008/9/1

Y1 - 2008/9/1

N2 - In this paper we propose a dimension reduction method for estimating the directions in a multiple-index regression based on information extraction. This extends the recent work of Yin and Cook [X. Yin, R.D. Cook, Direction estimation in single-index regression, Biometrika 92 (2005) 371-384] who introduced the method and used it to estimate the direction in a single-index regression. While a formal extension seems conceptually straightforward, there is a fundamentally new aspect of our extension: We are able to show that, under the assumption of elliptical predictors, the estimation of multiple-index regressions can be decomposed into successive single-index estimation problems. This significantly reduces the computational complexity, because the nonparametric procedure involves only a one-dimensional search at each stage. In addition, we developed a permutation test to assist in estimating the dimension of a multiple-index regression.

AB - In this paper we propose a dimension reduction method for estimating the directions in a multiple-index regression based on information extraction. This extends the recent work of Yin and Cook [X. Yin, R.D. Cook, Direction estimation in single-index regression, Biometrika 92 (2005) 371-384] who introduced the method and used it to estimate the direction in a single-index regression. While a formal extension seems conceptually straightforward, there is a fundamentally new aspect of our extension: We are able to show that, under the assumption of elliptical predictors, the estimation of multiple-index regressions can be decomposed into successive single-index estimation problems. This significantly reduces the computational complexity, because the nonparametric procedure involves only a one-dimensional search at each stage. In addition, we developed a permutation test to assist in estimating the dimension of a multiple-index regression.

UR - http://www.scopus.com/inward/record.url?scp=48749099148&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=48749099148&partnerID=8YFLogxK

U2 - 10.1016/j.jmva.2008.01.006

DO - 10.1016/j.jmva.2008.01.006

M3 - Article

AN - SCOPUS:48749099148

VL - 99

SP - 1733

EP - 1757

JO - Journal of Multivariate Analysis

JF - Journal of Multivariate Analysis

SN - 0047-259X

IS - 8

ER -