Skip to main content

AN ADAPTIVE COMPOSITE QUANTILE APPROACH TO DIMENSION REDUCTION

Kong, Efang (2014) AN ADAPTIVE COMPOSITE QUANTILE APPROACH TO DIMENSION REDUCTION. Annals of Statistics, 42 (4). pp. 1657-1688. ISSN 0090-5364. (doi:10.1214/14-AOS1242) (KAR id:41213)

PDF Author's Accepted Manuscript
Language: English
Download (1MB) Preview
[thumbnail of AOS1242.pdf]
Preview
This file may not be suitable for users of assistive technology.
Request an accessible format
Official URL
https://projecteuclid.org/euclid.aos/1407420012#ab...

Abstract

Sufficient dimension reduction [Li 1991] 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.

Item Type: Article
DOI/Identification number: 10.1214/14-AOS1242
Uncontrolled keywords: Bahadur approximation; sufficient dimension reduction; local polynomial smoothing; quantile regression; semiparametric models; U-processes
Subjects: Q Science > QA Mathematics (inc Computing science) > QA276 Mathematical statistics
Divisions: Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Mathematics, Statistics and Actuarial Science
Depositing User: Efang Kong
Date Deposited: 29 May 2014 13:44 UTC
Last Modified: 16 Feb 2021 12:53 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/41213 (The current URI for this page, for reference purposes)
  • Depositors only (login required):

Downloads

Downloads per month over past year