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

A Bayesian hierarchical approach for combining case-control and prospective studies.

P Müller1, G Parmigiani, J Schildkraut

  • 1Institute of Statistics and Decision Sciences, Duke University, Durham, North Carolina 27708-0251, USA. pm@isds.duke.edu

Biometrics
|April 21, 2001
PubMed
Summary

This study introduces a novel hierarchical approach for analyzing combined case-control and prospective studies to predict disease risk. The method simplifies risk factor analysis and Bayesian predictions, enhancing medical decision-making.

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

Shared and Study-specific Dietary Patterns and Head and Neck Cancer Risk in an International Consortium.

Epidemiology (Cambridge, Mass.)·2018
Same author

Expressed fusion gene landscape and its impact in multiple myeloma.

Nature communications·2017
Same author

Treatment decision-making capacity in non-consensual psychiatric treatment: a multicentre study.

Epidemiology and psychiatric sciences·2017
Same author

Survival in women with ovarian cancer with and without microsatellite instability.

European journal of gynaecological oncology·2016
Same author

Cost-effectiveness of alternative strategies for integrating MRI into breast cancer screening for women at high risk.

British journal of cancer·2014
Same author

Frequency of mutations in mismatch repair genes in a population-based study of women with ovarian cancer.

British journal of cancer·2012

Area of Science:

  • Epidemiology
  • Biostatistics
  • Medical Decision Making

Background:

  • Accurate absolute risk prediction is crucial for medical decision-making and patient counseling.
  • Existing methods often struggle to effectively combine diverse study designs like case-control and prospective studies.
  • Parameter heterogeneity across studies and within studies complicates risk factor analysis.

Purpose of the Study:

  • To propose a novel hierarchical approach for the combined analysis of case-control and prospective studies.
  • To simplify the computation of Bayesian predictions in hierarchical case-control settings.
  • To provide a flexible modeling strategy for disease risk factor inference.

Main Methods:

  • A hierarchical modeling approach is employed to address parameter heterogeneity.

Related Experiment Videos

  • The core strategy involves modeling the retrospective distribution of covariates given the disease outcome.
  • Mixture models are used for retrospective covariate distributions, enabling a general nonlinear regression family for the prospective likelihood.
  • Markov chain Monte Carlo (MCMC) methods are developed for inference and prediction.

    • Main Results:

    • The proposed retrospective modeling approach simplifies the combination of prospective and retrospective data.
    • The method allows for flexible modeling of covariate distributions, leading to a general nonlinear prospective likelihood.
    • Demonstrated the approach's relationship with existing methods through theoretical results.
    • Successfully applied the method to ovarian cancer data for illustration.

    Conclusions:

    • The developed hierarchical approach offers a unified framework for analyzing combined case-control and prospective studies.
    • Retrospective modeling provides a more flexible and computationally tractable alternative to traditional prospective modeling for risk factor inference.
    • This method enhances the accuracy of absolute risk predictions, supporting improved medical decision-making and patient counseling.