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

[Analysis of longitudinal Gaussian data with missing data on the response variable].

H Jacqmin-Gadda¹, D Commenges, J Dartigues

¹INSERM U330, 146 rue Léo Saignat, 33076 Bordeaux Cedex.

Revue D'Epidemiologie Et De Sante Publique

|February 16, 2000

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

Ginkgo Biloba Extract Consumption and Long-Term Occurrence of Death and Dementia.

The journal of prevention of Alzheimer's disease·2017

Same author

Measuring cognitive change in subjects with prodromal Alzheimer's disease.

Journal of neurology, neurosurgery, and psychiatry·2013

Same author

Dynamical models of biomarkers and clinical progression for personalized medicine: the HIV context.

Advanced drug delivery reviews·2013

Same author

A simple score to predict survival with dementia in the general population.

Neuroepidemiology·2013

Same author

Joint model with latent state for longitudinal and multistate data.

Biostatistics (Oxford, England)·2011

Same author

Estimation of the distribution of infection times using longitudinal serological markers of HIV: implications for the estimation of HIV incidence.

Biometrics·2010

Same journal

[Advocacy and recommendations for better positioning of epidemiologists during future epidemics and pandemics].

Revue d'epidemiologie et de sante publique·2024

Same journal

Vient de paraître.

Revue d'epidemiologie et de sante publique·2024

Same journal

Revue d'epidemiologie et de sante publique·2024

Same journal

Vient de paraître.

Revue d'epidemiologie et de sante publique·2024

Same journal

VIENT DE PARAÎTRE.

Revue d'epidemiologie et de sante publique·2024

Same journal

Revue d'epidemiologie et de sante publique·2024

See all related articles

Missing data in longitudinal studies can bias results. The Diggle and Kenward (DK) method offers a way to handle non-ignorable missing data, but careful application and comparison with simpler methods are recommended for Gaussian outcomes.

Area of Science:

Biostatistics
Longitudinal Data Analysis
Missing Data Methods

Context:

Longitudinal studies frequently encounter missing outcome data, potentially biasing results.
Gaussian longitudinal data analysis commonly employs mixed-effects linear models.
Assessing the impact of missing data and selecting appropriate statistical methods is crucial.

Purpose:

To demonstrate the bias introduced by missing outcome data in Gaussian longitudinal studies.
To discuss and evaluate statistical methods for handling missing data, including ignorable and non-ignorable types.
To compare the performance of the Diggle and Kenward (DK) method with standard approaches.

Summary:

A simulation study and analysis of the Paquid cohort data illustrate bias from naive analysis of missing longitudinal data.

Related Experiment Videos

The DK method, combining linear mixed-effects and logistic models, is presented for non-ignorable missing data.

While effective for Gaussian data, the DK method's performance can be suboptimal with non-normal data; comparing results with ignorable missing data hypotheses is advised.

Impact:

Highlights the critical need for appropriate statistical methods to mitigate bias in longitudinal studies with missing data.
Provides practical guidance on applying the DK method and emphasizes the importance of sensitivity analyses.
Suggests the need for further software development to facilitate robust analysis of complex missing data scenarios in longitudinal research.