Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

A comparative study of feature screening methods for ultrahigh dimensional multiclass classification

Authors
Lee, KyungeunKim, Kyoung HeeShin, Seung Jun
Issue Date
10월-2017
Publisher
KOREAN STATISTICAL SOC
Keywords
multi-categorical classification; simulation; ultrahigh-dimensional classification
Citation
KOREAN JOURNAL OF APPLIED STATISTICS, v.30, no.5, pp.793 - 808
Indexed
KCI
Journal Title
KOREAN JOURNAL OF APPLIED STATISTICS
Volume
30
Number
5
Start Page
793
End Page
808
URI
https://scholar.korea.ac.kr/handle/2021.sw.korea/82017
DOI
10.5351/KJAS.2017.30.5.793
ISSN
1225-066X
Abstract
We compare various variable screening methods on multiclass classification problems when the data is ultrahigh-dimensional. Two different approaches were considered: (1) pairwise extension from binary classification via one versus one or one versus rest comparisons and (2) direct classification of multiclass responses. We conducted extensive simulation studies under different conditions: heavy tailed explanatory variables, correlated signal and noise variables, correlated joint distributions but uncorrelated marginals, and unbalanced response variables. We then analyzed real data to examine the performance of the methods. The results showed that model-free methods perform better for multiclass classification problems as well as binary ones.
Files in This Item
There are no files associated with this item.
Appears in
Collections
College of Political Science & Economics > Department of Statistics > 1. Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Altmetrics

Total Views & Downloads

BROWSE