Expectile Regression for Censored Data Based on Data Augmentation
Biometrical Journal · 2026-04 · 68 (2)
DOI: 10.1002/bimj.70118 ↗Kurz gefasst
Fachartikel in der Zeitschrift Biometrical Journal, online erschienen am 27.02.2026. Verfasst von Wei Cao und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Economics and Management, Beihang University, Beijing, China. Hauptthemen laut MEDLINE: Biometry. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 46 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Statistical modeling and estimation for heterogeneous censored survival data is of great practical importance, as exemplified by applications in bio‐medicine. Censored quantile and expectile regression methods offer useful tools to capture heterogeneity in the set of covariates at different locations of the survival distribution. The former is computationally challenging due to the non‐smooth nature of the check loss, and the later employs the inverse probability of censoring weighting (IPW) technique, which involves the unknown survival function of censored times and is designed for right‐censored data. In this article, we investigate the expectile regression for censored data to capture its heterogeneity and develop a novel and unified estimation method for various types of censoring mechanisms. To handle the censoring, we employ the data augmentation approach instead of IPW, without estimating the survival function of the censored times. Extensive simulation studies are carried out to evaluate the performance of the proposed approach and also two real datasets are analyzed, obtaining some intriguing findings. The proposed algorithm has been implemented into an R function, DAer .
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Economics and Management, Beihang University, Beijing, China.
- MIIT Key Laboratory of Data Intelligence and Management, Beihang University, Beijing, China.
ORCID-Profile: Shanshan Wang
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Cao, W., Wang, S., & Zhong, H. (2026). Expectile Regression for Censored Data Based on Data Augmentation. Biometrical Journal, 68(2). https://doi.org/10.1002/bimj.70118
Vancouver
Cao W, Wang S, Zhong H. Expectile Regression for Censored Data Based on Data Augmentation. Biometrical Journal. 2026;68(2). doi:10.1002/bimj.70118
BibTeX
@article{Cao2026,
author = {Cao, Wei and Wang, Shanshan and Zhong, Hanyu},
title = {Expectile Regression for Censored Data Based on Data Augmentation},
journal = {Biometrical Journal},
year = {2026},
volume = {68},
number = {2},
doi = {10.1002/bimj.70118}
}
EUVIMED