EUVIMEDEUVIMED entdecken
Open Access

Bayesian multiple imputation for functional data

Ziren Jiang iD, Lei Xuan, Eric F Lock iD, Erjia Cui

Biometrics · 2026

DOI: 10.1093/biomtc/ujag182 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biometrics, 2026. Verfasst von Ziren Jiang und 3 weiteren Autor:innen. Beteiligte Einrichtung: Division of Biostatistics and Health Data Science, School of Public Health, University of Minnesota, Minneapolis, MN 55414, United States. Hauptthemen laut MEDLINE: Models, Statistical. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIH HHS, National Institutes of Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Missing data are pervasive in modern functional datasets, where trajectories are often sparsely or irregularly observed. Although functional principal component analysis is widely used to reconstruct incomplete curves, existing approaches typically employ single imputation, leading to overly optimistic inferences in downstream analyses. To address these challenges, we develop a novel Bayesian multiple imputation framework for functional data (BAMIFun). For single-level functional data, we impose a Bayesian low-rank model that incorporates penalized spline representations to enforce smoothness of the functional domain and derive an efficient Gibbs sampler algorithm for posterior computation. In addition, we demonstrate and validate how to properly account for estimation uncertainties in downstream analysis. Furthermore, we extend the framework to multiway functional data using Functional Tensor Singular Value Decomposition model, enabling Bayesian multiple imputation in settings not supported by existing methods. Simulation studies show that BAMIFun achieves substantially improved coverage and more reliable downstream inference compared to existing methods, while maintaining similar imputation accuracy. Case studies using a physical activity dataset and an infant gut microbiome dataset further demonstrate the practical advantages of our proposed methods under severe missingness.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Models, StatisticalBayes TheoremComputer SimulationAlgorithmsHumansData Interpretation, StatisticalBiometry

Stichwörter der Autor:innen

Bayesian inferencefunctional data analysismissing datamultiple imputationmultiway data

Autor:innen und Institutionen

  • Division of Biostatistics and Health Data Science, School of Public Health, University of Minnesota, Minneapolis, MN 55414, United States.

ORCID-Profile: Ziren Jiang, Eric F Lock

Förderung

  • NIH HHS
  • National Institutes of Health

Zitieren

APA

Jiang, Z., Xuan, L., Lock, E. F., & Cui, E. (2026). Bayesian multiple imputation for functional data. Biometrics. https://doi.org/10.1093/biomtc/ujag182

Vancouver

Jiang Z, Xuan L, Lock EF, Cui E. Bayesian multiple imputation for functional data. Biometrics. 2026. doi:10.1093/biomtc/ujag182

BibTeX
@article{Jiang2026,
  author = {Jiang, Ziren and Xuan, Lei and Lock, Eric F and Cui, Erjia},
  title = {Bayesian multiple imputation for functional data},
  journal = {Biometrics},
  year = {2026},
  doi = {10.1093/biomtc/ujag182}
}
Kostenlos starten →