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

Collapsing ordered outcome categories: a note of concern

U Strömberg1

  • 1Department of Occupational and Environmental Medicine, University Hospital, Lund University, Sweden.

American Journal of Epidemiology
|August 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

Colorectal cancer screening with fecal immunochemical testing or primary colonoscopy: An analysis of health equity based on a randomised trial.

EClinicalMedicine·2022
Same author

In-hospital vs. 30-day mortality in the critically ill - a 2-year Swedish intensive care cohort analysis.

Acta anaesthesiologica Scandinavica·2015
Same author

Autologous haematopoietic stem cell transplantation: a viable treatment option for CIDP.

Journal of neurology, neurosurgery, and psychiatry·2013
Same author

Chromosomal aberrations and SCEs as biomarkers of cancer risk.

Mutation research·2006
Same author

Yearly measurements of blood lead in Swedish children since 1978: an update focusing on the petrol lead free period 1995-2001.

Occupational and environmental medicine·2003
Same author

Retrospective exposure assessment and quality control in an international multi-centre case-control study.

The Annals of occupational hygiene·2002

Collapsing ordinal outcomes in epidemiologic studies can affect results. Be cautious when dichotomizing outcome variables, as it may alter effect estimates and inferences.

Area of Science:

  • Epidemiology
  • Biostatistics

Background:

  • Ordinal outcomes are common in epidemiologic research.
  • The proportional odds model is frequently used for analyzing such data.
  • Collapsing outcome categories is a potential simplification strategy.

Purpose of the Study:

  • To investigate the impact of collapsing ordinal outcome variables on effect estimates.
  • To assess the consequences of outcome variable dichotomization in proportional odds models.
  • To provide guidance on appropriate data analysis for ordinal outcomes.

Main Methods:

  • Analysis of epidemiologic data with ordinal outcomes.
  • Application of the proportional odds model.
  • Comparison of effect estimates using measured versus collapsed/dichotomized outcome variables.

Related Experiment Videos

Main Results:

  • Collapsing outcome categories can alter effect estimates and statistical inference.
  • Dichotomizing ordinal outcomes requires careful consideration to avoid misleading results.
  • The proportional odds model's efficiency may be maintained with collapsed variables in some cases.

Conclusions:

  • Researchers must exercise caution when modifying ordinal outcome variables.
  • The choice of outcome variable structure significantly influences study findings.
  • Appropriate statistical methods are crucial for accurate interpretation of epidemiologic data.