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

Accurate variance estimation for prevalence ratios.

M Wolkewitz1, T Bruckner, M Schumacher

  • 1Institute of Medical Biometry and Medical Informatics, University Medical Center Freiburg, Stefan-Meier-Str. 26, 79104 Freiburg, and Department of Clinical and Social Medicine, University Hospital Heidelberg, Germany. wolke@fdm.uni-freiburg.de

Methods of Information in Medicine
|October 17, 2007
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

Twenty-seven years follow-up of a patient with congenital retinocephalofacial vascular malformation syndrome and additional congenital malformations (Bonnet-Dechaume-Blanc syndrome or Wyburn-Mason syndrome).

European journal of medical research·2010
Same author

An experimental evaluation of boosting methods for classification.

Methods of information in medicine·2010
Same author

[Perioperative management in outpatient arthroscopy of the knee joint].

Zeitschrift fur Orthopadie und Unfallchirurgie·2010
Same author

[Studer ileum neobladder].

Aktuelle Urologie·2010
Same author

Membrane progesterone receptors localization in the mouse spinal cord.

Neuroscience·2009
Same author

[Temporary transvenous embolization of a giant arteriovenous fistula of the scalp--a preoperative option].

RoFo : Fortschritte auf dem Gebiete der Rontgenstrahlen und der Nuklearmedizin·2009
Same journal

Design and methodological development of a digital clinical safety training programme informed by a national framework: a New Zealand case study.

Methods of information in medicine·2026
Same journal

Panic Prediction from Digital Phenotyping: Subject-Level Cross-Validation Reveals Limited Between-Person Generalization.

Methods of information in medicine·2026
Same journal

Agent-Based Modeling Approach for Population Dynamics of the Biological Vector Aedes Aegypti.

Methods of information in medicine·2026
Same journal

A Statistical Framework for Person-centered Analysis of Digital Service Use in Public Health and Social Care.

Methods of information in medicine·2026
Same journal

Assessing the Quality of Electronic Discharge Summaries: A Cross-Sectional Study Using the Validated Spanish Version of the PDQI-9.

Methods of information in medicine·2026
Same journal

A Knowledge Graph-Driven Hypergeometric Efficacy Prediction Model for Classical Traditional Chinese Herbal Formulas.

Methods of information in medicine·2026
See all related articles

For calculating prevalence ratios in cross-sectional studies, the log-binomial model can be unstable. If it fails, the Poisson model with a robust variance is recommended for reliable results.

Area of Science:

  • Epidemiology
  • Biostatistics

Background:

  • The log-binomial model is standard for prevalence ratio estimation in cross-sectional studies with binary outcomes.
  • Numerical instability can cause convergence issues with the log-binomial model.
  • Alternative methods are needed when the log-binomial model fails.

Purpose of the Study:

  • To compare different adjustments for the Poisson model when the log-binomial model fails.
  • To evaluate the performance of adjusted Poisson models against the log-binomial model for prevalence ratio calculation.

Main Methods:

  • Simulated data were used to assess Poisson models with robust variance, Pearson's chi-square adjustment, and deviance adjustment.
  • Model performance was evaluated based on hypothesis testing, considering confounding and effect modification.

Related Experiment Videos

  • Comparison was made against the log-binomial model.

    • Main Results:

    • All tested Poisson model adjustments improved variance estimation compared to unadjusted models.
    • The Poisson model with a robust variance demonstrated the best performance.
    • The log-binomial model provided acceptable power and Type I error rates even when unstable.
    • The Poisson model with Pearson's chi-square adjustment also yielded favorable results.

    Conclusions:

    • The Poisson model with a robust variance estimate is recommended when the log-binomial model fails to converge for prevalence ratio estimation.
    • This approach offers a reliable alternative for analyzing binary outcomes in cross-sectional studies.