SIMEX –Trans: High‐Dimensional Transfer Learning With Covariates Subject to Measurement Error
Statistics in Medicine · 2026-11 · 45 (25-27)
DOI: 10.1002/sim.70820 ↗Kurz gefasst
Fachartikel in der Zeitschrift Statistics in Medicine, online erschienen am 11.11.2026. Verfasst von Kaida Cai und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Epidemiology and Biostatistics, Southeast University, Nanjing, China. Hauptthemen laut MEDLINE: Models, Statistical, Gene Expression Profiling. Die Arbeit nennt 31 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Jiangsu Province, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
Gene expression studies typically involve small sample sizes, high‐dimensional covariates, and measurement error, posing significant challenges for accurate statistical modeling. We propose simulation–extrapolation (SIMEX)–based high‐dimensional transfer learning methods (SIMEX–Trans) that (i) correct measurement error and (ii) leverage information from informative auxiliary studies. We consider settings where the informative auxiliary studies are either known or unknown, and develop Lasso‐ and SCAD‐penalized estimators. When the informative studies are known, we establish support recovery and asymptotic normality for the SIMEX‐based SCAD‐penalized estimator. Simulation results show that SIMEX–Trans outperforms competing methods in estimation accuracy and achieves reliable variable selection performance. In a GTEx brain‐tissue analysis of cross‐tissue prediction of hypothalamus JAM2 expression with limited target samples and heterogeneous auxiliary tissues, the proposed SIMEX–Trans–Selector approach achieves the lowest cross‐validated prediction error and remains stable under sensitivity analysis.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Epidemiology and Biostatistics, Southeast University, Nanjing, China.
- Department of Statistics and Actuarial Science, Southeast University, Nanjing, China.
- School of Mathematics and Statistics, University of Melbourne, Melbourne, Australia.
ORCID-Profile: Kaida Cai
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Jiangsu Province
- Fundamental Research Funds for the Central Universities
Zitieren
APA
Cai, K., Wang, Z., Chen, H., & Liu, H. (2026). SIMEX –Trans: High‐Dimensional Transfer Learning With Covariates Subject to Measurement Error. Statistics in Medicine, 45(25-27). https://doi.org/10.1002/sim.70820
Vancouver
Cai K, Wang Z, Chen H, Liu H. SIMEX –Trans: High‐Dimensional Transfer Learning With Covariates Subject to Measurement Error. Statistics in Medicine. 2026;45(25-27). doi:10.1002/sim.70820
BibTeX
@article{Cai2026,
author = {Cai, Kaida and Wang, Zhengyan and Chen, Hanning and Liu, Hanwen},
title = {SIMEX –Trans: High‐Dimensional Transfer Learning With Covariates Subject to Measurement Error},
journal = {Statistics in Medicine},
year = {2026},
volume = {45},
number = {25-27},
doi = {10.1002/sim.70820}
}
EUVIMED