EUVIMEDOdkrijte EUVIMED
Open access · CC BY-NC-ND 4.0

Likelihood‐Based Non‐Parametric Receiver Operating Characteristic Curve Analysis in the Presence of Imperfect Reference Standard

Yifan Sun, Peijun Sang iD, Qinglong Tian iD, Pengfei Li iD

Statistics in Medicine · 2025

DOI: 10.1002/sim.70327 ↗

At a glance

Journal article in Statistics in Medicine, 2025. Written by Yifan Sun and 3 co-authors. Institution: Department of Statistics and Actuarial Science, University of Waterloo, Waterloo, Canada. Major MEDLINE topics: ROC Curve. Cited 1 times so far (Crossref); 36 references. The full text is freely available (open access, CC BY-NC-ND 4.0). Funded by: Natural Sciences and Engineering Research Council of Canada, Faculty of Mathematics Research Chair funding at the University of Waterloo.

PovzetekSubjectsBibliografski podatkiCiteRelated studies

Abstract (original language)

In diagnostic studies, researchers frequently encounter imperfect reference standards with some misclassified labels. Treating these as gold standards can bias receiver operating characteristic (ROC) curve analysis. To address this issue, we propose a novel likelihood‐based method under a non‐parametric density ratio model. This approach enables the reliable estimation of the ROC curve, area under the curve (AUC), partial AUC, and Youden's index with favorable statistical properties. To implement the method, we develop an efficient expectation‐maximization (EM) algorithm. Extensive simulations evaluate its finite‐sample performance, showing smaller mean squared errors in estimating the ROC curve, partial AUC, and Youden's index compared to existing methods. We apply the proposed approach to a malaria study.

Subjects

MeSH terms (MEDLINE)

ROC CurveHumansLikelihood FunctionsAlgorithmsComputer SimulationReference StandardsMalariaArea Under CurveStatistics, NonparametricModels, Statistical

Author keywords

EM algorithmcase‐control studylikelihood functionmixture modelsieve estimation

Authors and institutions

  • Department of Statistics and Actuarial Science, University of Waterloo, Waterloo, Canada.

ORCID profiles: Peijun Sang, Qinglong Tian, Pengfei Li

Funding

  • Natural Sciences and Engineering Research Council of Canada
  • Faculty of Mathematics Research Chair funding at the University of Waterloo

Cite

APA

Sun, Y., Sang, P., Tian, Q., & Li, P. (2025). Likelihood‐Based Non‐Parametric Receiver Operating Characteristic Curve Analysis in the Presence of Imperfect Reference Standard. Statistics in Medicine. https://doi.org/10.1002/sim.70327

Vancouver

Sun Y, Sang P, Tian Q, Li P. Likelihood‐Based Non‐Parametric Receiver Operating Characteristic Curve Analysis in the Presence of Imperfect Reference Standard. Statistics in Medicine. 2025. doi:10.1002/sim.70327

BibTeX
@article{Sun2025,
  author = {Sun, Yifan and Sang, Peijun and Tian, Qinglong and Li, Pengfei},
  title = {Likelihood‐Based Non‐Parametric Receiver Operating Characteristic Curve Analysis in the Presence of Imperfect Reference Standard},
  journal = {Statistics in Medicine},
  year = {2025},
  doi = {10.1002/sim.70327}
}
Start for free →