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

Selecting the best method to evaluate bronchodilation when analysing bronchodilator studies.

Dick M Goedhart1, Pieter Zanen

  • 1Cardialysis, Westblaak 92, 3012 RM, Rotterdam, The Netherlands.

Statistics in Medicine
|November 19, 2002
PubMed
Summary

Statistical analysis of lung function changes, specifically forced expiratory volume in 1 second (FEV1), is best performed using analysis of covariance. This method offers superior statistical power and avoids issues like residual heterogeneity common in analysis of variance.

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

Vitamin K2 Supplementation in Hospitalised COVID-19 Patients: A Randomised Controlled Trial.

Journal of clinical medicine·2024
Same author

Waiting List Dynamics and Lung Transplantation Outcomes After Introduction of the Lung Allocation Score in The Netherlands.

Transplantation direct·2021
Same author

<i>Post hoc</i> analysis of a randomised controlled trial: effect of vitamin D supplementation on circulating levels of desmosine in COPD.

ERJ open research·2020
Same author

Serum biomarker CA 15-3 as predictor of response to antifibrotic treatment and survival in idiopathic pulmonary fibrosis.

Biomarkers in medicine·2020
Same author

Results of the standard set for pulmonary sarcoidosis: feasibility and multicentre outcomes.

ERJ open research·2019
Same author

<i>In vivo</i> growth of 60 non-screening detected lung cancers: a computed tomography study.

The European respiratory journal·2018

Area of Science:

  • Pulmonary Medicine
  • Biostatistics
  • Clinical Trials

Background:

  • Lung function changes, particularly forced expiratory volume in 1 second (FEV1), are frequently reported as percentages of predicted values.
  • The suitability of these percentage-based metrics for robust statistical analysis in clinical trials remains a key question.

Purpose of the Study:

  • To evaluate the statistical performance of different methods for analyzing bronchodilation test results.
  • To identify the optimal statistical approach for assessing changes in FEV1 during bronchodilation trials.

Main Methods:

  • Analysis of 2199 bronchodilation tests, extracting pre- and post-dilator FEV1, age, height, and sex.
  • Calculation of predicted FEV1, FEV1 difference, and percentage change relative to predicted or baseline FEV1.

Related Experiment Videos

  • Comparison of analysis of variance (ANOVA) and analysis of covariance (ANCOVA) on these parameters, assessing statistical power and residual structures.

    • Main Results:

    • Both ANOVA of percentage change and ANCOVA of absolute FEV1 demonstrated strong performance.
    • ANOVA revealed funnel-shaped residuals, indicating heterogeneity, power loss, and alpha-level deviations.
    • ANCOVA did not exhibit these residual issues, suggesting greater statistical robustness.

    Conclusions:

    • Analysis of covariance is the preferred method for evaluating bronchodilation in clinical trials due to its robustness against residual heterogeneity.
    • Standard sample size calculations may be inaccurate when using ANOVA for bronchodilation data due to unaddressed residual issues.