EUVIMEDEUVIMED entdecken
Crossref

Leveraging independence in high-dimensional mixed linear regression

Ning Wang, Kai Deng, Qing Mai iD, Xin Zhang iD

Biometrics · 2024

DOI: 10.1093/biomtc/ujae103 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biometrics, 2024. Verfasst von Ning Wang und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Statistics, Beijing Normal University, Zhuhai, 519000, China. Hauptthemen laut MEDLINE: Computer Simulation, Algorithms. Die Arbeit nennt 34 Literaturangaben. Gefördert von: National Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We address the challenge of estimating regression coefficients and selecting relevant predictors in the context of mixed linear regression in high dimensions, where the number of predictors greatly exceeds the sample size. Recent advancements in this field have centered on incorporating sparsity-inducing penalties into the expectation-maximization (EM) algorithm, which seeks to maximize the conditional likelihood of the response given the predictors. However, existing procedures often treat predictors as fixed or overlook their inherent variability. In this paper, we leverage the independence between the predictor and the latent indicator variable of mixtures to facilitate efficient computation and also achieve synergistic variable selection across all mixture components. We establish the non-asymptotic convergence rate of the proposed fast group-penalized EM estimator to the true regression parameters. The effectiveness of our method is demonstrated through extensive simulations and an application to the Cancer Cell Line Encyclopedia dataset for the prediction of anticancer drug sensitivity.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Computer SimulationAlgorithmsHumansLinear ModelsLikelihood FunctionsAntineoplastic AgentsCell Line, TumorNeoplasmsSample SizeModels, StatisticalBiometry

Stichwörter der Autor:innen

EM algorithmfinite mixture modelgroup lassolatent variable model

Substanzen

Antineoplastic Agents

Autor:innen und Institutionen

  • Department of Statistics, Beijing Normal University, Zhuhai, 519000, China.
  • Department of Statistics, Florida State University, Tallahassee, Florida 32312, United States.

ORCID-Profile: Qing Mai, Xin Zhang

Förderung

  • National Science Foundation

Zitieren

APA

Wang, N., Deng, K., Mai, Q., & Zhang, X. (2024). Leveraging independence in high-dimensional mixed linear regression. Biometrics. https://doi.org/10.1093/biomtc/ujae103

Vancouver

Wang N, Deng K, Mai Q, Zhang X. Leveraging independence in high-dimensional mixed linear regression. Biometrics. 2024. doi:10.1093/biomtc/ujae103

BibTeX
@article{Wang2024,
  author = {Wang, Ning and Deng, Kai and Mai, Qing and Zhang, Xin},
  title = {Leveraging independence in high-dimensional mixed linear regression},
  journal = {Biometrics},
  year = {2024},
  doi = {10.1093/biomtc/ujae103}
}
Kostenlos starten →