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

The discrepancy in discrepant analysis

A Hadgu1

  • 1Centers for Disease Control and Prevention, Center for HIV, STD, and TB prevention, Atlanta, GA 30333, USA.

Lancet (London, England)
|August 31, 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

Seasonal patterns of tuberculosis case notification in the tropics of Africa: A six-year trend analysis in Ethiopia.

PloS one·2018
Same author

Reproducibility and specificity concerns associated with nucleic acid amplification tests for detecting Chlamydia trachomatis.

European journal of clinical microbiology & infectious diseases : official publication of the European Society of Clinical Microbiology·2008
Same author

Prevalence of genital chlamydial infection in young women entering a national job training program, 1990-1997.

American journal of public health·2001
Same author

A GEE approach to estimating sensitivity and specificity and coverage properties of the confidence intervals.

Statistics in medicine·2001
Same author

Using a combination of reference tests to assess the accuracy of a diagnostic test by A. Alonzo and M. Pepe, Statistics in Medicine 1999; 18: 2987-3003.

Statistics in medicine·2001
Same author

Discrepant analysis is an inappropriate and unscientific method.

Journal of clinical microbiology·2001
Same journal

Convergence of metabolic risk in obesity and normal BMI: does risk disappear?

Lancet (London, England)·2026
Same journal

Metabolic traits in obesity and normal BMI in industrialised countries: a multi-country analysis of national population-based studies.

Lancet (London, England)·2026
Same journal

Safety and efficacy of mRNA vaccines: a mechanistic and public health perspective.

Lancet (London, England)·2026
Same journal

The US Ebola response and the future of global health leadership.

Lancet (London, England)·2026
Same journal

Daniel Mason: a tale of change.

Lancet (London, England)·2026
Same journal

The 2026 Wakley-Wu Lien Teh Prize Essay: why medicine, and why stay?

Lancet (London, England)·2026
See all related articles

Discrepant analysis overestimates diagnostic test performance, even with perfect resolution. This method is unreliable for evaluating sensitivity and specificity of tests like Chlamydia trachomatis DNA-amplification assays.

Area of Science:

  • Medical diagnostics
  • Infectious disease testing
  • Molecular diagnostics

Background:

  • Discrepant analysis is a common method for estimating diagnostic test accuracy when a perfect gold standard is unavailable.
  • It has been applied to assess DNA-amplification tests for Chlamydia trachomatis, including ligase chain-reaction and polymerase chain-reaction assays.
  • Concerns exist regarding the reliability of estimates derived from this technique.

Purpose of the Study:

  • To evaluate the accuracy of discrepant analysis in estimating diagnostic test performance.
  • To determine if upward bias in sensitivity and specificity estimates persists even with perfect discrepant result resolution.
  • To provide recommendations on the use of discrepant analysis for diagnostic test evaluation.

Main Methods:

Related Experiment Videos

  • The study critically reviews the application and statistical properties of discrepant analysis.
  • It analyzes the impact of an imperfect gold standard on sensitivity and specificity estimations.
  • The effect of using a perfect test for resolving discrepancies is theoretically examined.

Main Results:

  • Estimates of sensitivity and specificity derived from discrepant analysis are consistently upwardly biased.
  • This upward bias in performance estimates remains even when a perfect test is employed to resolve discrepant results.
  • The inherent limitations of discrepant analysis lead to overestimation of test accuracy.

Conclusions:

  • Discrepant analysis should not be adopted for evaluating the performance of diagnostic tests due to inherent upward bias.
  • The technique provides unreliable sensitivity and specificity estimates, potentially misrepresenting test accuracy.
  • Researchers should consider alternative methods for diagnostic test performance evaluation in the absence of a perfect gold standard.