Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

Akaike's information criterion in generalized estimating equations.

¹Division of Biostatistics, University of Minnesota, Minneapolis 55455, USA. weip@biostat.umn.edu

|March 17, 2001

Summary

This study introduces a new model-selection criterion for generalized estimating equations (GEE) by modifying the Akaike Information Criterion (AIC). This addresses a gap in statistical methods for correlated biomedical data.

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

Developing and evaluating definitions of real-world clinical endpoints for patients with early-stage triple-negative breast cancer using a United States of America secondary database.

ESMO real world data and digital oncology·2026

Same author

[Echocardiographic characteristics and prognostic evaluation of Ebstein anomaly in fetuses].

Zhonghua er ke za zhi = Chinese journal of pediatrics·2025

Same author

Trajectories of physiological stress markers over time among Latinx immigrants in the United States: Influences of acculturative stressors and psychosocial resilience.

Social science & medicine (1982)·2024

Same author

Inhibitor of apoptosis proteins (IAP) inhibitor APG-1387 monotherapy or in combination with programmed cell death 1 (PD-1) inhibitor toripalimab in patients with advanced solid tumors: results from two phase I trials.

ESMO open·2024

Same author

Retraction Note: MiR-1294 acts as a tumor suppressor in clear cell renal cell carcinoma through targeting HOXA6.

European review for medical and pharmacological sciences·2024

Same author

Interplay of metabolic dysfunction-associated fatty liver disease and papillary thyroid carcinoma: insights from a Chinese cohort.

Journal of endocrinological investigation·2024

Area of Science:

Biostatistics
Statistical modeling
Biomedical data analysis

Background:

Correlated response data are prevalent in biomedical research.
Generalized estimating equations (GEE) are crucial for analyzing such data.
Limited model-selection criteria exist for GEE.

Purpose of the Study:

To propose a novel model-selection criterion for GEE.
To adapt the Akaike Information Criterion (AIC) for non-likelihood-based GEE.
To evaluate the performance of the proposed criterion.

Main Methods:

Modification of the Akaike Information Criterion (AIC).
Replacement of likelihood with quasi-likelihood in AIC.
Adjustment of the penalty term for GEE.

Related Experiment Videos

Simulation studies to assess performance.

Application to a real biomedical dataset.

Main Results:

The proposed modified AIC provides a viable model-selection tool for GEE.
Simulation results demonstrate the effectiveness of the new criterion.
The method is applicable to real-world biomedical data analysis.

Conclusions:

The modified AIC offers a valuable approach for model selection in GEE.
This enhances the analytical capabilities for correlated biomedical data.
Further research can explore extensions and applications of this method.