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

Multivariate methods for clustered ordinal data with applications to survival analysis

B Rosner1, R J Glynn

  • 1Channing Laboratory, Harvard Medical School, Boston, MA 02115, USA.

Statistics in Medicine
|February 28, 1997
PubMed
Summary

This study introduces new statistical methods for analyzing clustered ordinal data, common in ophthalmology. The developed models effectively handle correlated outcomes in clinical research, improving analysis for conditions like cataracts and diabetic retinopathy.

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

Simultaneous mapping of the ultrafast time and fluence dependence of the laser-induced insulator-to-metal transition in magnetite.

Structural dynamics (Melville, N.Y.)·2025
Same author

Maternal rotating night shift work before pregnancy and offspring stress markers.

Physiology & behavior·2019
Same author

Rotating night shift work and menopausal age.

Human reproduction (Oxford, England)·2019
Same author

Towards X-ray transient grating spectroscopy.

Optics letters·2019
Same author

Different menopausal hormone regimens and risk of breast cancer.

Annals of oncology : official journal of the European Society for Medical Oncology·2018
Same author

Consumption of soy foods and isoflavones and risk of type 2 diabetes: a pooled analysis of three US cohorts.

European journal of clinical nutrition·2016

Area of Science:

  • Biostatistics
  • Ophthalmology
  • Medical Statistics

Background:

  • Clustered data are prevalent in clinical specialties like ophthalmology, particularly for ordinal outcomes such as cataract and diabetic retinopathy grading.
  • Existing statistical methods struggle to adequately incorporate clustering effects into the analysis of ordinal data.
  • There is a need for robust statistical models to address clustered ordinal outcomes in clinical research.

Purpose of the Study:

  • To develop and present novel statistical methodologies for the analysis of clustered ordinal outcome data.
  • To extend existing models to effectively account for correlated observations within clusters, specifically in ophthalmological and survival data.
  • To provide a flexible framework for analyzing complex clinical data where outcomes are ordered and clustered.

Related Experiment Videos

Main Methods:

  • Proposed a generalization of the adjacent category model for clustered ordinal data, incorporating a clustering parameter.
  • Derived closed-form expressions for probabilities and utilized the Newton-Raphson method for likelihood maximization.
  • Extended the methodology to a survival analysis setting to accommodate both censored and uncensored clustered outcomes.

Main Results:

  • Successfully applied the developed methods to analyze cortical cataract grades in diabetic subjects.
  • Demonstrated the utility of the survival analysis extension using data on otitis media development in children.
  • The proposed models provide a statistically sound approach to handling clustered ordinal data in clinical settings.

Conclusions:

  • The novel statistical methods effectively address the challenge of analyzing clustered ordinal data in clinical research.
  • These methodologies offer significant improvements for analyzing ophthalmological data and extend to survival analysis scenarios.
  • The developed models enhance the ability to draw accurate conclusions from correlated clinical outcome data.