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

On modeling longitudinal pulmonary function data

D Sherrill1, G Viegi

  • 1Respiratory Sciences Center, College of Medicine, University of Arizona, Tucson 85724, USA.

American Journal of Respiratory and Critical Care Medicine
|December 1, 1996
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

Asthma and allergies in schoolchildren: data from the European SINPHONIE study.

The international journal of tuberculosis and lung disease : the official journal of the International Union against Tuberculosis and Lung Disease·2025
Same author

Health status of Italian children living close to cultivations sprayed with pesticides.

The international journal of tuberculosis and lung disease : the official journal of the International Union against Tuberculosis and Lung Disease·2024
Same author

Asthma incidence can be influenced by climate change in Italy: findings from the GEIRD study-a climatological and epidemiological assessment.

Scientific reports·2023
Same author

Issue 2 - "Update on adverse respiratory effects of indoor air pollution". Part 2): Indoor air pollution and respiratory diseases: Perspectives from Italy and some other GARD countries.

Pulmonology·2023
Same author

COPD treatment - a conceptual review based on critical endpoints.

Pulmonology·2023
Same author

Outdoor air pollution and respiratory health.

The international journal of tuberculosis and lung disease : the official journal of the International Union against Tuberculosis and Lung Disease·2023
Same journal

How the Exposome Shapes Our Respiratory Health.

American journal of respiratory and critical care medicine·2026
Same journal

Diagnostic criteria for invasive pulmonary aspergillosis in COPD patients.

American journal of respiratory and critical care medicine·2026
Same journal

Opportunities for Human Lung Tissue-Based Studies in Fibrotic ILD Research.

American journal of respiratory and critical care medicine·2026
Same journal

Astegolimab in COPD: success or failure?

American journal of respiratory and critical care medicine·2026
Same journal

How artificial intelligence could improve the diagnosis and management of COPD: a perspective from GOLD.

American journal of respiratory and critical care medicine·2026
Same journal

Awake ECMO for ARDS: No Vent, No VILI, No Problem?

American journal of respiratory and critical care medicine·2026
See all related articles

This study explores random effects models for analyzing respiratory data. It recommends restricted maximum likelihood (REML) for continuous data and generalized estimating equations (GEE) for categorical data, aiding in model selection and outlier detection.

Area of Science:

  • Biostatistics
  • Respiratory Medicine
  • Longitudinal Data Analysis

Background:

  • Longitudinal and categorical respiratory data analysis requires appropriate statistical modeling.
  • Linear models with random effects offer flexibility for complex data structures.

Purpose of the Study:

  • To discuss the application of random effects in linear models for pulmonary function and respiratory data.
  • To guide the selection of appropriate methods (REML and GEE) based on data characteristics.
  • To detail the process of model specification and validation for longitudinal respiratory studies.

Main Methods:

  • Review of restricted maximum likelihood (REML) for normally distributed data and generalized estimating equations (GEE) for categorical/non-normal data.
  • Application of parallel plots and within-subject regression fitting for determining random effects order.

Related Experiment Videos

  • Demonstration of selecting error structures, random effects, covariance matrices, and fixed effects using FEV1 data.
  • Illustration of conditional and marginal residual plots for outlier and trend detection.

    • Main Results:

    • REML is suitable for continuous, normally distributed or transformable data.
    • GEE is appropriate for categorical or non-normally distributed data.
    • Methods for selecting model components and validating model fit were demonstrated.
    • Residual plots aid in identifying data anomalies and model underfitting.

    Conclusions:

    • The choice between REML and GEE depends on the nature of respiratory data (continuous vs. categorical).
    • Systematic approaches to model selection and validation are crucial for accurate analysis.
    • Available software may not support all discussed REML and GEE modeling options.