Feature Screening for Ultrahigh Dimensional Mixed Data via Wasserstein Distance
International Statistical Review · 2025-08 · 93 (2) · 267-287
DOI: 10.1111/insr.12609 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Statistical Review, online erschienen am 15.02.2025. Verfasst von Bing Tian und 1 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 29 Literaturangaben.
Abstract (Originalsprache)
This article develops a novel feature screening procedure for ultrahigh dimensional mixed data based on Wasserstein distance, termed as Wasserstein‐SIS. To handle the mixture of continuous and discrete data, we use Wasserstein distance as a new marginal utility to measure the difference between the joint distribution and the product of marginal distributions. In theory, we establish the sure screening property under less restrictive assumptions on data types. The proposed procedure does not require model specification, gives a more effective geometric measure to compare the discrepancy between distributions and avoids introducing biases caused by the choice of slicing rules for continuous data. Numerical comparison indicates that the proposed Wasserstein‐SIS method performs better than existing methods in various models. A real data application also validates the better practicability of Wasserstein‐SIS.
Zitieren
APA
Tian, B., & Wang, H. (2025). Feature Screening for Ultrahigh Dimensional Mixed Data via Wasserstein Distance. International Statistical Review, 93(2), 267-287. https://doi.org/10.1111/insr.12609
Vancouver
Tian B, Wang H. Feature Screening for Ultrahigh Dimensional Mixed Data via Wasserstein Distance. International Statistical Review. 2025;93(2):267-287. doi:10.1111/insr.12609
BibTeX
@article{Tian2025,
author = {Tian, Bing and Wang, Hong},
title = {Feature Screening for Ultrahigh Dimensional Mixed Data via Wasserstein Distance},
journal = {International Statistical Review},
year = {2025},
volume = {93},
number = {2},
pages = {267--287},
doi = {10.1111/insr.12609}
}
EUVIMED