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

Secondary analysis of case-control data.

Yannan Jiang1, Alastair J Scott, Chris J Wild

  • 1Department of Statistics, The University of Auckland, Private Bag 92019, Auckland, New Zealand.

Statistics in Medicine
|October 13, 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

Early Amino Acid Intake in ELBW Infants: School-Aged Outcomes From a Randomized Controlled Trial.

Pediatrics·2026
Same author

Early Nutrition, Blood Amino Acids and Outcomes in Preterm Babies: Secondary Cohort Analysis of the ProVIDe RCT.

Nutrients·2026
Same author

Postnatal conditional growth and size and body composition at 24 months in moderate-and-late preterm children.

Pediatric research·2026
Same author

Machine Learning-Based Prediction Model Construction for Type 2 Diabetes Mellitus: A Comparison of Algorithms and Multilevel Risk Factor Analysis.

Journal of diabetes research·2026
Same author

Validation of Guillain-Barré syndrome case identification in three heterogeneous VAC4EU real-world data sources in Spain using the Brighton Collaboration criteria.

Vaccine·2026
Same author

Sodium, potassium and iodine excretion and blood pressure of New Zealand school children: a cross-sectional study and comparison with recommended guidelines.

BMJ nutrition, prevention & health·2026
Same journal

A Mixture of Distributed Lag Non-Linear Models to Account for Spatially Heterogeneous Exposure-Lag-Response Associations.

Statistics in medicine·2026
Same journal

Practical Considerations for Gaussian Process Modeling for Causal Inference in Quasi-Experimental Studies With Panel Data.

Statistics in medicine·2026
Same journal

Covariate Adjustment for Wilcoxon Two Sample Statistic and Test.

Statistics in medicine·2026
Same journal

Beyond Fixed Thresholds: Optimizing Summaries of Wearable Device Data via Piecewise Linearization of Quantile Functions.

Statistics in medicine·2026
Same journal

A Causal Framework for Evaluating the Total Effect of Strategies Aiming to Expand Screening and to Improve Outcomes.

Statistics in medicine·2026
Same journal

Causal Effects on Nonterminal Event Time With Application to Antibiotic Usage and Future Resistance.

Statistics in medicine·2026
See all related articles

Common methods for analyzing case-control data can yield misleading results, especially for rare cases. Researchers should use both weighted likelihood and semi-parametric maximum likelihood methods for robust and efficient analysis.

Area of Science:

  • Epidemiology
  • Biostatistics

Background:

  • Secondary analysis of case-control data is common in epidemiological research.
  • Existing ad hoc methods may lead to inaccurate conclusions.

Purpose of the Study:

  • To investigate the efficiency and robustness of different methods for secondary analysis of case-control data.
  • To compare ad hoc methods with weighted likelihood and semi-parametric maximum likelihood methods.

Main Methods:

  • Extensive investigation of efficiency and robustness of various analytical strategies.
  • Theoretical justification and practical comparison of weighted likelihood and semi-parametric maximum likelihood (SPML) methods.

Main Results:

  • Ad hoc methods often produce misleading conclusions, particularly when cases are rare.

Related Experiment Videos

  • SPML is more efficient but sensitive to nuisance model mis-specification.
  • Weighted likelihood is robust to nuisance model mis-specification but can be inefficient.

    • Conclusions:

    • Practitioners should routinely employ both weighted likelihood and SPML methods.
    • The choice of method requires balancing efficiency against robustness based on specific research contexts.