EUVIMEDEUVIMED entdecken
Open Access

Improving prediction of linear regression models by integrating external information from heterogeneous populations: James–Stein estimators

Peisong Han iD, Haoyue Li, Sung Kyun Park iD, Bhramar Mukherjee iD, Jeremy M G Taylor

Biometrics · 01.07.2024 · 80 (3)

DOI: 10.1093/biomtc/ujae072 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biometrics, online erschienen am 05.08.2024. Verfasst von Peisong Han und 4 weiteren Autor:innen. Beteiligte Einrichtung: Biostatistics Innovation Group, Gilead Sciences, 333 Lakeside Drive, Foster City, CA 94404, United States. Hauptthemen laut MEDLINE: Computer Simulation. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIEHS NIH HHS, NIA NIH HHS, NCI NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We consider the setting where (1) an internal study builds a linear regression model for prediction based on individual-level data, (2) some external studies have fitted similar linear regression models that use only subsets of the covariates and provide coefficient estimates for the reduced models without individual-level data, and (3) there is heterogeneity across these study populations. The goal is to integrate the external model summary information into fitting the internal model to improve prediction accuracy. We adapt the James–Stein shrinkage method to propose estimators that are no worse and are oftentimes better in the prediction mean squared error after information integration, regardless of the degree of study population heterogeneity. We conduct comprehensive simulation studies to investigate the numerical performance of the proposed estimators. We also apply the method to enhance a prediction model for patella bone lead level in terms of blood lead level and other covariates by integrating summary information from published literature.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Computer SimulationHumansLinear ModelsBiometryLeadPatellaModels, StatisticalData Interpretation, Statistical

Stichwörter der Autor:innen

James–Stein shrinkagedata integrationexternal summary informationmeta-analysispopulation heterogeneityprediction mean squared error

Substanzen

Lead

Autor:innen und Institutionen

  • Biostatistics Innovation Group, Gilead Sciences, 333 Lakeside Drive, Foster City, CA 94404, United States.
  • Department of Biostatistics, University of Michigan, 1415 Washington Heights, Ann Arbor, MI 48109, United States.
  • Department of Epidemiology, University of Michigan, 1415 Washington Heights, Ann Arbor, MI 48109, United States.

ORCID-Profile: Peisong Han, Sung Kyun Park, Bhramar Mukherjee

Förderung

  • NIEHS NIH HHS
  • NIA NIH HHS
  • NCI NIH HHS
  • NIH HHS
  • National Institutes of Health

Zitieren

APA

Han, P., Li, H., Park, S. K., Mukherjee, B., & Taylor, J. M. G. (2024). Improving prediction of linear regression models by integrating external information from heterogeneous populations: James–Stein estimators. Biometrics, 80(3). https://doi.org/10.1093/biomtc/ujae072

Vancouver

Han P, Li H, Park SK, Mukherjee B, Taylor JMG. Improving prediction of linear regression models by integrating external information from heterogeneous populations: James–Stein estimators. Biometrics. 2024;80(3). doi:10.1093/biomtc/ujae072

BibTeX
@article{Han2024,
  author = {Han, Peisong and Li, Haoyue and Park, Sung Kyun and Mukherjee, Bhramar and Taylor, Jeremy M G},
  title = {Improving prediction of linear regression models by integrating external information from heterogeneous populations: James–Stein estimators},
  journal = {Biometrics},
  year = {2024},
  volume = {80},
  number = {3},
  doi = {10.1093/biomtc/ujae072}
}
Kostenlos starten →