Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Confidence bands for receiver operating characteristic curves

G Ma1, W J Hall

  • 1Department of Biostatistics, University of Rochester Medical Center, New York.

Medical Decision Making : an International Journal of the Society for Medical Decision Making
|July 1, 1993
PubMed
Summary

This study introduces new methods for constructing confidence bands for Receiver Operating Characteristic (ROC) curves. These techniques improve the statistical reliability of ROC curve analysis in medical diagnostics.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

[Clinicopathologic features and prognosis of retroperitoneal unicentric Castleman disease: report of 38 patients].

Zhonghua wei chang wai ke za zhi = Chinese journal of gastrointestinal surgery·2026
Same author

[Reasonable extent of No.12a lymph node dissection in laparoscopic surgery for locally advanced distal gastric cancer].

Zhonghua wei chang wai ke za zhi = Chinese journal of gastrointestinal surgery·2026
Same author

[Optimal duration of preoperative imatinib therapy in locally advanced gastrointestinal stromal tumors].

Zhonghua zhong liu za zhi [Chinese journal of oncology]·2025
Same author

MFSnet: a multi-scale feature screening network for chicken counting in dense environments.

British poultry science·2025
Same author

Integrating genomics and transcriptomics to identify candidate genes for high-altitude adaptation and egg production in Nixi chicken.

British poultry science·2024
Same author

[The influence of Ras-associated binding protein 23 knockdown on the migration and invasion of esophageal squamous cell carcinoma cells and its mechanism].

Zhonghua zhong liu za zhi [Chinese journal of oncology]·2024

Area of Science:

  • Statistics
  • Medical Diagnostics
  • Biostatistics

Background:

  • Receiver Operating Characteristic (ROC) curves are crucial for evaluating diagnostic test performance.
  • Current methods for ROC curve analysis have limitations in providing reliable confidence intervals.
  • Variations in decision thresholds generate trade-offs between sensitivity and specificity, defining the ROC curve.

Purpose of the Study:

  • To develop novel statistical methods for constructing simultaneous confidence bands for ROC curves.
  • To enhance the precision and reliability of ROC curve analysis, particularly under the binormal model.
  • To provide robust statistical tools for assessing diagnostic accuracy.

Main Methods:

  • Employed Working-Hotelling-type confidence bands from simple linear regression to construct ROC curve confidence bands.

Related Experiment Videos

  • Focused on scenarios with asymptotically normally distributed parameter estimates and consistent variance-covariance matrices.
  • Developed methods applicable to both entire and partial ROC curves, extending beyond the binormal model.

    • Main Results:

    • Successfully constructed two-sided and one-sided simultaneous confidence bands for ROC curves.
    • Demonstrated the utility of these bands for both entire and partial curve analyses.
    • Presented pointwise confidence bands for comparative analysis, highlighting the advantages of simultaneous bands.

    Conclusions:

    • The developed methods offer statistically sound and reliable confidence bands for ROC curve analysis.
    • These techniques enhance the interpretation of diagnostic test performance by providing more robust uncertainty estimates.
    • The proposed methodology is versatile and extends beyond traditional binormal ROC models.