Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Penalized principal logistic regression for sparse sufficient dimension reduction

Shin, Seung Jun and Artemiou, Andreas 2017. Penalized principal logistic regression for sparse sufficient dimension reduction. Computational Statistics & Data Analysis 111 , pp. 48-58. 10.1016/j.csda.2016.12.003

[img]
Preview
PDF - Accepted Post-Print Version
Download (550kB) | Preview

Abstract

Sufficient dimension reduction (SDR) is a successive tool for reducing the dimensionality of predictors by finding the central subspace, a minimal subspace of predictors that preserves all the regression information. When predictor dimension is large, it is often assumed that only a small number of predictors is informative. In this regard, sparse SDR is desired to achieve variable selection and dimension reduction simultaneously. We propose a principal logistic regression (PLR) as a new SDR tool and extend it to a penalized version for sparse SDR. Asymptotic analysis shows that the penalized PLR enjoys the oracle property. Numerical investigation supports the advantageous performance of the proposed methods.

Item Type: Article
Date Type: Publication
Status: Published
Schools: Mathematics
Subjects: Q Science > QA Mathematics
Uncontrolled Keywords: Max-SCAD penalty; Principal logistic regression; Sparse sufficient dimension reduction; Sufficient dimension reduction
Publisher: Elsevier
ISSN: 0167-9473
Date of First Compliant Deposit: 9 December 2016
Date of Acceptance: 5 December 2016
Last Modified: 29 Dec 2017 08:53
URI: http://orca.cf.ac.uk/id/eprint/96679

Citation Data

Cited 2 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item Edit Item

Downloads

Downloads per month over past year

View more statistics