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

Statistical inference for correlated data in ophthalmologic studies.

Man-Lai Tang1, Nian-Sheng Tang, Bernard Rosner

  • 1Department of Mathematics, Hong Kong Baptist University, Kowloon, Hong Kong. mltang@math.hkbu.edu.hk

Statistics in Medicine
|December 29, 2005
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

Effect of icosapent ethyl treatment on colorectal tissue marine omega-3 polyunsaturated fatty acid levels among patients with a history of adenoma: a prospective, single-arm clinical trial.

The American journal of clinical nutrition·2026
Same author

A multi-state survival model to identify risk factors for lethal ovarian cancer.

Cancer epidemiology, biomarkers & prevention : a publication of the American Association for Cancer Research, cosponsored by the American Society of Preventive Oncology·2026
Same author

Associations of alcohol use with expression of stromal markers in benign breast biopsy samples.

British journal of cancer·2026
Same author

Reliability of stromal markers multiplex immunofluorescent staining: pathologist assessment compared to quantitative image analysis.

American journal of cancer research·2026
Same author

Spatially Correlated Analysis of Infectious Disease Outcomes Based on Bayesian Functional Hierarchical Models.

Statistics in medicine·2026
Same author

Associations of oral contraceptives with expression of CD44, CD24, and ALDH1A1 stem cell markers in women with benign breast biopsies.

Breast cancer research : BCR·2026

Accurate statistical testing is crucial in ophthalmology for paired eye data. New approximate unconditional procedures offer reliable type I error rates, unlike exact methods that can be too conservative for small sample sizes.

Area of Science:

  • Ophthalmology
  • Biostatistics
  • Clinical Trials

Background:

  • Ophthalmologic studies often involve paired data from two eyes, which exhibit high intraclass correlation.
  • Ignoring this correlation in binary paired data analysis can inflate significance levels.
  • Existing methods, even those accounting for correlation, may yield unacceptable Type I error rates with small sample sizes or sparse data.

Purpose of the Study:

  • To propose and evaluate novel statistical procedures for binary paired data in ophthalmology.
  • To address limitations of existing methods regarding Type I error control in small or sparse datasets.
  • To introduce exact unconditional and approximate unconditional procedures as alternatives.

Main Methods:

  • Simulation studies were conducted to compare the performance of proposed methods against existing ones.

Related Experiment Videos

  • Evaluation focused on Type I error rates under various conditions, including small sample sizes and sparse data.
  • Methodologies were illustrated using a real-world dataset from a retinal detachment study.

    • Main Results:

    • Exact unconditional procedures demonstrated overly conservative empirical Type I error rates, significantly underestimating nominal levels.
    • Approximate unconditional procedures consistently yielded empirical Type I error rates close to the pre-assigned nominal level.
    • The proposed approximate unconditional procedures showed superior performance in maintaining desired error rates.

    Conclusions:

    • Approximate unconditional procedures are recommended for statistical testing of binary paired data in ophthalmology, especially with small or sparse sample sizes.
    • These methods provide a more reliable control of Type I error rates compared to exact unconditional procedures.
    • The findings enhance the accuracy and validity of statistical inferences in ophthalmologic research.