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

Imputation of missing data when measuring physical activity by accelerometry.

Diane J Catellier1, Peter J Hannan, David M Murray

  • 1Department of Biostatistics, University of North Carolina, Chapel Hill, NC 27514-4145, USA. diane_catellier@unc.edu

Medicine and Science in Sports and Exercise
|November 19, 2005
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

CRT-Estimands Framework: consensus based extension of the ICH E9(R1) addendum for cluster randomised trials.

BMJ (Clinical research ed.)·2026
Same author

Early-Life Factors and Body Mass Index Trajectories Among Children in the ECHO Cohort.

JAMA network open·2025
Same author

Improving the design and analytic methods used in NIH-funded clinical trials involving behavioral interventions.

Annals of behavioral medicine : a publication of the Society of Behavioral Medicine·2025
Same author

Prenatal Diet and Infant Growth From Birth to Age 24 Months.

JAMA network open·2024
Same author

Evaluating analytic models for individually randomized group treatment trials with complex clustering in nested and crossed designs.

Statistics in medicine·2024
Same author

Design and Analytic Methods to Evaluate Multilevel Interventions to Reduce Health Disparities: Rigorous Methods Are Available.

Prevention science : the official journal of the Society for Prevention Research·2024
Same journal

Cardiorespiratory Fitness and Age-Related Decline in Kidney Function among Individuals with Preserved Kidney Health: The Aging Kidney Study.

Medicine and science in sports and exercise·2026
Same journal

Objectively Measured Cardiorespiratory Fitness as a Potential Biomarker for Alzheimer's Disease Risk in Older Adults: Evidence from the Generation 100 Study.

Medicine and science in sports and exercise·2026
Same journal

The Effects of Eight-Week Traditional Aerobic Exercise and Exergaming on Dual-Task Performance and Prefrontal Cortex Activation in Older Adults.

Medicine and science in sports and exercise·2026
Same journal

The Impact of Cardiorespiratory Fitness on Cytotoxic T Cell Metabolism and Function.

Medicine and science in sports and exercise·2026
Same journal

Female Athletes Through the Lifespan: Clinical Considerations and a Call for Comprehensive Sports Medicine Healthcare.

Medicine and science in sports and exercise·2026
Same journal

Artificial Intelligence in Exercise Science and Sports Medicine.

Medicine and science in sports and exercise·2026
See all related articles

Imputing missing accelerometer data improves physical activity estimates. This method reduces bias and increases precision, especially when data is missing non-randomly.

Area of Science:

  • Biomedical data analysis
  • Physical activity monitoring
  • Wearable sensor technology

Background:

  • Accelerometer data is crucial for assessing physical activity.
  • Non-uniform wear time leads to biased activity estimates.
  • Missing data can underestimate daily physical activity levels.

Purpose of the Study:

  • To address bias in accelerometer data due to missing wear time.
  • To evaluate imputation methods for improving physical activity estimation.
  • To investigate bias reduction in activity counts from intermittent missing data.

Main Methods:

  • Utilized data from the Trial for Activity in Adolescent Girls (TAAG).
  • Simulated missing accelerometer data (random and systematic missingness).

Related Experiment Videos

  • Compared observed data analysis with single (EM algorithm) and multiple imputation (MI).

    • Main Results:

    • Imputation yielded more precise activity estimates than observed data when missingness was random.
    • Imputation significantly reduced bias in activity estimates with systematic missing data.
    • Both single imputation (EM) and multiple imputation (MI) performed comparably.

    Conclusions:

    • Missing value imputation is recommended for accelerometer data analysis.
    • Imputation enhances precision and reduces bias in physical activity estimates.
    • Software for imputation should be utilized by researchers studying physical activity.