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

1996 Remington lecture: modeling multivariate longitudinal data that are incomplete.

M A Espeland1, T E Craven, M E Miller

  • 1Section on Biostatistics, Wake Forest University School of Medicine, Winston-Salem, NC 27157-1063, USA.

Annals of Epidemiology
|April 7, 1999
PubMed
Summary

Addressing missing data in longitudinal multivariate analyses is crucial for accurate model selection. Ignoring missing data mechanisms can lead to inefficient and potentially biased results, especially when missingness is substantial.

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

The relationship between repeated measurements of HbA<sub>1c</sub> and risk of coronary events among the common haptoglobin phenotype groups: the Action for Health in Diabetes (Look AHEAD) study.

Cardiovascular diabetology·2024
Same author

Erratum to: Association between Modifiable Risk Factors and Levels of Blood-Based Biomarkers of Alzheimer's and Related Dementias in the Look AHEAD Cohort.

JAR life·2024
Same author

Association between Modifiable Risk Factors and Levels of Blood-Based Biomarkers of Alzheimer's and Related Dementias in the Look AHEAD Cohort.

JAR life·2024
Same author

Daytime Sleepiness Is Associated with Lower Cognitive Scores: The Look AHEAD Study.

JAR life·2023
Same author

Interactions between estradiol, diabetes, and brain aging and the risk for cognitive impairment.

Climacteric : the journal of the International Menopause Society·2021
Same author

Sustaining eHealth engagement in a multi-year weight gain prevention intervention.

Obesity science & practice·2019

Area of Science:

  • Biostatistics
  • Medical Data Analysis
  • Longitudinal Studies

Background:

  • Missing data can significantly impact model selection in longitudinal multivariate analyses.
  • The Asymptomatic Carotid Artery Progression Study (ACAPS) provided ultrasonographic measurements for this investigation.
  • Understanding missing data mechanisms is vital for robust statistical modeling.

Discussion:

  • Maximum likelihood estimation was employed to fit various models to the ACAPS ultrasonographic data.
  • Graphical methods were utilized to assess the patterns and potential mechanisms of missing data.
  • The study highlights the consequences of not accounting for missing data in statistical analyses.

Key Insights:

  • Statistical methods that appropriately handle missing data enhance analytical efficiency.

Related Experiment Videos

  • Complex models with segment-specific parameterizations for longitudinal correlations may satisfy the missing-at-random assumption.
  • Ignoring missing data, particularly when prevalent, can lead to serious analytical drawbacks.

    • Outlook:

    • Future research should focus on developing and validating advanced statistical techniques for handling missing data in complex longitudinal datasets.
    • Implementing robust missing data strategies is essential for reliable scientific conclusions in medical research.
    • High-dimensional models and maximum likelihood techniques may be necessary for appropriate missing data handling, potentially improving statistical efficiency.