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

A generalized linear model for analysing receiver operating characteristic curves

P J Smith1, T J Thompson, M M Engelgau

  • 1Centers for Disease Control and Prevention, Division of Tuberculosis Elimination (E-10), Atlanta, GA 30333, USA.

Statistics in Medicine
|February 15, 1996
PubMed
Summary
This summary is machine-generated.

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

A multivariate logistic regression equation to screen for dysglycaemia: development and validation.

Diabetic medicine : a journal of the British Diabetic Association·2005
Same author

Controlling the diabetes epidemic: how should we screen for undiagnosed diabetes and dysglycaemia?

Diabetic medicine : a journal of the British Diabetic Association·2005
Same author

Finding undiagnosed type 2 diabetes: is it worth the effort?

Effective clinical practice : ECP·2002
Same author

Performance of recommended screening tests for undiagnosed diabetes and dysglycemia.

Diabetes care·2001
Same author

The Diabetes Quality Improvement Project: moving science into health policy to gain an edge on the diabetes epidemic.

Diabetes care·2001
Same author

Use of diabetes preventive care and complications risk in two African-American communities.

American journal of preventive medicine·2001

We introduce a new continuation ratio model for analyzing ordinal data and estimating receiver operating characteristic (ROC) curves. This method provides accurate sensitivity and specificity estimates for diabetes screening using blood glucose levels.

Area of Science:

  • Statistics
  • Medical Diagnostics
  • Biometry

Background:

  • Ordinal categorical data analysis is crucial in medical research.
  • Estimating receiver operating characteristic (ROC) curves is essential for evaluating diagnostic tests.
  • Existing ROC models may lack flexibility in curve shape.

Purpose of the Study:

  • To present a novel continuation ratio model for ordinal data analysis.
  • To apply this model for estimating ROC curves.
  • To evaluate its performance in the context of diabetes mellitus screening.

Main Methods:

  • Development of a continuation ratio model for ordinal categorical data.
  • Application of the model to estimate ROC curves.
  • Utilizing post-prandial capillary blood glucose measurements for diabetes screening.

Related Experiment Videos

Main Results:

  • The continuation ratio model allows for point estimates of sensitivity and specificity with standard errors.
  • ROC curves generated by this model can be concave but not necessarily symmetric.
  • Comparison with Tosteson and Begg's models highlights desirable features of the new approach.

Conclusions:

  • The continuation ratio model offers a flexible and robust method for ROC curve analysis.
  • This approach is applicable to medical screening tests, such as for diabetes mellitus.
  • The model provides valuable statistical insights into diagnostic test performance.