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

Re-using data from case-control studies

A J Lee1, L McMurchy, A J Scott

  • 1Department of Statistics, University of Auckland, New Zealand.

Statistics in Medicine
|June 30, 1997
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

Neonatal acid-base status before and after discontinuing routine left uterine displacement for elective cesarean delivery: a retrospective cohort study (2014-2017).

International journal of obstetric anesthesia·2025
Same author

Ethnic disparities in obstetric anaesthesia care in England: parallels and paradoxes with care in the USA.

Anaesthesia·2023
Same author

Evolution of SARS-CoV-2 mutational variants: Hysteria or hope for the future?

African journal of thoracic and critical care medicine·2022
Same author

Mentorship during undergraduate surgical training: comparing perceptions of medical students and faculty at two institutions in South Africa and Sweden.

South African journal of surgery. Suid-Afrikaanse tydskrif vir chirurgie·2021
Same author

The impact of disability on performance in a high-stakes postgraduate surgical examination: a retrospective cohort study.

Journal of the Royal Society of Medicine·2021
Same author

A cross-sectional study examining the association between MRCS performance and surgeons receiving sanctions against their medical registration.

The surgeon : journal of the Royal Colleges of Surgeons of Edinburgh and Ireland·2021

Case-control studies offer efficiency but yield non-representative samples. This research presents a method to correct biased regression coefficients in secondary analyses of case-control data when the sampling rates are known.

Area of Science:

  • Biostatistics
  • Epidemiology
  • Statistical Modeling

Background:

  • Case-control sampling is cost-effective for maximizing statistical power but produces non-representative population samples.
  • Standard logistic regression in case-control studies yields biased constant terms but unbiased covariate coefficients when the stratification variable is the response.
  • Secondary analyses using a previous covariate as the response can lead to biased regression coefficients if associated with the stratification variable.

Purpose of the Study:

  • To address the bias in regression coefficient estimates during secondary analyses of case-control studies.
  • To present a method for calculating maximum likelihood estimates for all regression coefficients when sampling rates are known.
  • To investigate situations where bias may not occur, building upon previous work by Nagelkerke et al.

Related Experiment Videos

Main Methods:

  • Develop and discuss a maximum likelihood estimation approach for logistic regression models.
  • Incorporate known sampling rates for cases and controls into the estimation procedure.
  • Apply the method to real-world data from the New Zealand Cot Death Study for validation.

Main Results:

  • The proposed method allows for the calculation of unbiased maximum likelihood estimates for all regression coefficients in secondary analyses.
  • Demonstrates the practical application and effectiveness of the method using a relevant epidemiological dataset.
  • Provides a statistically sound approach to overcome bias issues inherent in certain case-control data re-analyses.

Conclusions:

  • The developed method effectively corrects for bias in regression coefficients when re-analyzing case-control data.
  • This approach enhances the utility of case-control studies by enabling reliable secondary analyses.
  • Accurate statistical modeling is crucial for valid inference from case-control studies, particularly in secondary analyses.