EUVIMEDEUVIMED entdecken
Crossref

Unit information Dirichlet process prior

Jiaqi Gu iD, Guosheng Yin iD

Biometrics · 2024

DOI: 10.1093/biomtc/ujae091 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biometrics, 2024. Verfasst von Jiaqi Gu und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Neurology and Neurological Sciences, Stanford University, Stanford, CA 94304, United States. Hauptthemen laut MEDLINE: Bayes Theorem, Markov Chains, Monte Carlo Method, Models, Statistical. Die Arbeit nennt 19 Literaturangaben. Gefördert von: Research Grants Council of Hong Kong.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Prior distributions, which represent one’s belief in the distributions of unknown parameters before observing the data, impact Bayesian inference in a critical and fundamental way. With the ability to incorporate external information from expert opinions or historical datasets, the priors, if specified appropriately, can improve the statistical efficiency of Bayesian inference. In survival analysis, based on the concept of unit information (UI) under parametric models, we propose the unit information Dirichlet process (UIDP) as a new class of nonparametric priors for the underlying distribution of time-to-event data. By deriving the Fisher information in terms of the differential of the cumulative hazard function, the UIDP prior is formulated to match its prior UI with the weighted average of UI in historical datasets and thus can utilize both parametric and nonparametric information provided by historical datasets. With a Markov chain Monte Carlo algorithm, simulations and real data analysis demonstrate that the UIDP prior can adaptively borrow historical information and improve statistical efficiency in survival analysis.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Bayes TheoremMarkov ChainsMonte Carlo MethodModels, StatisticalComputer SimulationSurvival AnalysisHumansAlgorithmsBiometryData Interpretation, Statistical

Stichwörter der Autor:innen

Bayesian nonparametricFisher informationMarkov chain Monte Carlohazard functiontime-to-event data

Autor:innen und Institutionen

  • Department of Neurology and Neurological Sciences, Stanford University, Stanford, CA 94304, United States.
  • Department of Statistics and Actuarial Science, University of Hong Kong, Hong Kong, 999077, China.

ORCID-Profile: Jiaqi Gu, Guosheng Yin

Förderung

  • Research Grants Council of Hong Kong

Zitieren

APA

Gu, J., & Yin, G. (2024). Unit information Dirichlet process prior. Biometrics. https://doi.org/10.1093/biomtc/ujae091

Vancouver

Gu J, Yin G. Unit information Dirichlet process prior. Biometrics. 2024. doi:10.1093/biomtc/ujae091

BibTeX
@article{Gu2024,
  author = {Gu, Jiaqi and Yin, Guosheng},
  title = {Unit information Dirichlet process prior},
  journal = {Biometrics},
  year = {2024},
  doi = {10.1093/biomtc/ujae091}
}
Kostenlos starten →