EUVIMEDEUVIMED entdecken
Crossref

A Modified Normalized Power Prior Approach for Bayesian Adaptive Borrowing in Item Response Theory Models

Qiang Zhang, Wei Xiong iD, Min Wang, Keying Ye, Zifei Han iD

Statistics in Medicine · 2026-05 · 45 (10-12)

DOI: 10.1002/sim.70568 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Statistics in Medicine, online erschienen am 30.04.2026. Verfasst von Qiang Zhang und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Statistics and Mathematics, Central University of Finance and Economics, Beijing, China. Hauptthemen laut MEDLINE: Models, Statistical. Die Arbeit nennt 45 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities, China in UIBE.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Questionnaires are widely used in clinical research and mental health studies, but their responses are usually more subjective than clinical biomarkers. Researchers may use latent variable models such as the item response theory (IRT) model to characterize individual ability, but response instability and small sample sizes can lead to increased uncertainty in estimation. Historical data from similar questionnaires may help reduce variation, but they must be incorporated adaptively. The challenge is further compounded by the need to ensure computational efficiency in IRT models with a large number of parameters. In this work, we develop a Bayesian framework for adaptive borrowing in IRT models based on an approximated normalized power prior (NPP) that treats the borrowing weight as a random parameter. The proposed method makes NPP feasible for general IRT models and is coupled with a full Bayesian data augmentation strategy that enables joint estimation of ability and item parameters through an efficient Gibbs sampler. In simulations, the approach adaptively increases borrowing when historical and current data are compatible and automatically downweights conflicting information. Relative to analyzes without borrowing, the method reduces variance and mean squared error while maintaining coverage across a range of test lengths, item discrimination profiles, and historical‐current concordance scenarios. We illustrate the method by integrating historical mental health surveys into current assessments, yielding more precise ability estimates with preserved calibration. An efficient implementation is provided in our updated package NPP available on the Comprehensive R Archive Network.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Models, StatisticalBayes TheoremHumansComputer SimulationSurveys and Questionnaires

Stichwörter der Autor:innen

Bayesian data augmentationadaptive borrowinghistorical informationitem response theorynormalized power prior

Autor:innen und Institutionen

  • School of Statistics and Mathematics, Central University of Finance and Economics, Beijing, China.
  • School of Statistics, University of International Business and Economics, Beijing, China.
  • Department of Statistics and Data Science, The University of Texas at San Antonio, San Antonio, Texas, USA.

ORCID-Profile: Wei Xiong, Zifei Han

Förderung

  • National Natural Science Foundation of China
  • Fundamental Research Funds for the Central Universities, China in UIBE

Zitieren

APA

Zhang, Q., Xiong, W., Wang, M., Ye, K., & Han, Z. (2026). A Modified Normalized Power Prior Approach for Bayesian Adaptive Borrowing in Item Response Theory Models. Statistics in Medicine, 45(10-12). https://doi.org/10.1002/sim.70568

Vancouver

Zhang Q, Xiong W, Wang M, Ye K, Han Z. A Modified Normalized Power Prior Approach for Bayesian Adaptive Borrowing in Item Response Theory Models. Statistics in Medicine. 2026;45(10-12). doi:10.1002/sim.70568

BibTeX
@article{Zhang2026,
  author = {Zhang, Qiang and Xiong, Wei and Wang, Min and Ye, Keying and Han, Zifei},
  title = {A Modified Normalized Power Prior Approach for Bayesian Adaptive Borrowing in Item Response Theory Models},
  journal = {Statistics in Medicine},
  year = {2026},
  volume = {45},
  number = {10-12},
  doi = {10.1002/sim.70568}
}
Kostenlos starten →