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

Bayesian inference on order-constrained parameters in generalized linear models.

David B Dunson1, Brian Neelon

  • 1Biostatistics Branch, National Institute of Environmental Health Sciences, MD A3-03, P.O. Box 12233, Research Triangle Park, North Carolina 27709, USA. dunson1@niehs.nih.gov

Biometrics
|August 21, 2003
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

Sequential Gibbs posteriors with applications to principal component analysis.

Biometrika·2026
Same author

Scalable and robust regression models for continuous proportional data.

Journal of the American Statistical Association·2026
Same author

Patient Preference Phenotypes for Post-operative Anticoagulation After Hip or Knee Replacement: A Cross-sectional Survey Study.

Journal of general internal medicine·2026
Same author

Local graph estimation with pathwise false discovery control.

Nature communications·2026
Same author

Bayesian Transfer Learning.

Statistical science : a review journal of the Institute of Mathematical Statistics·2026
Same author

Shifting perceptions of e-cigarette risk: A secondary analysis from a nationwide, randomized controlled clinical trial of e-cigarettes among smokers.

Addictive behaviors·2026
Same journal

Causally-interpretable random-effects meta-analysis.

Biometrics·2026
Same journal

Statistical inference for mean function of partially observed functional time series.

Biometrics·2026
Same journal

Subgroup identification via Interaction Tree and Mixed Model for Repeated Measures with application to Alzheimer's disease.

Biometrics·2026
Same journal

Finite mixtures of linear quantile regressions with concomitant variables: a solution to endogeneity in longitudinal data modeling.

Biometrics·2026
Same journal

Discussion on "INTACT: a method for integration of longitudinal physical activity data from multiple sources" by Jingru Zhang, Erjia Cui, Hongzhe Li, and Haochang Shou.

Biometrics·2026
Same journal

A Bayesian phase I/II platform design with data augmentation accounting for delayed outcomes.

Biometrics·2026
See all related articles

This study introduces a Bayesian method for analyzing ordered categorical predictors in generalized linear models. The approach uses isotonic regression for efficient inference and allows for flat trends, improving association tests in biomedical research.

Area of Science:

  • Biostatistics
  • Statistical Modeling
  • Bayesian Inference

Background:

  • Biomedical studies frequently assess associations between ordered categorical predictors and outcomes, adjusting for covariates.
  • Traditional methods include k-1 degree of freedom (df) tests or single df trend tests, often requiring pre-defined predictor level scores.
  • Incorporating monotonicity constraints can enhance the efficiency of association tests when the response function's parametric form is unknown.

Purpose of the Study:

  • To propose a general Bayesian approach for statistical inference on order-constrained parameters within generalized linear models.
  • To address computational challenges associated with priors directly on the constrained space.
  • To enable efficient computation of Bayes factors for ordered trends.

Main Methods:

Related Experiment Videos

  • A novel Bayesian approach is presented, mapping draws from an unconstrained posterior density using an isotonic regression transformation.
  • This method accommodates flat regions where predictor level increases do not affect the outcome.
  • Inference is facilitated by a Gibbs sampling algorithm, allowing for the computation of Bayes factors.

Main Results:

  • The proposed Bayesian method provides an efficient way to handle order-constrained parameters in generalized linear models.
  • The isotonic regression transformation simplifies computation and allows for flexible modeling of trends.
  • Simulation studies demonstrate the approach's utility, and it is applied to a time-to-pregnancy study.

Conclusions:

  • The developed Bayesian framework offers a computationally feasible and statistically robust method for analyzing ordered categorical predictors with monotonicity constraints.
  • This approach enhances the efficiency and interpretability of association tests in biomedical research.
  • The method is applicable to various generalized linear models and complex datasets, as shown in the time-to-pregnancy study example.