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

A test of missing completely at random for longitudinal data with missing observations

T Park¹, S Y Lee

¹Department of Statistics, Hankuk University of Foreign Studies, Korea.

Statistics in Medicine

|August 30, 1997

Summary

This study introduces a practical method to test assumptions in longitudinal data analysis. It addresses potential biases when missing data are not completely random, improving the reliability of generalized estimating equations.

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

Preconditioning regulation of bcl-2 and p66shc by human NOS1 enhances tolerance to oxidative stress.

FASEB journal : official publication of the Federation of American Societies for Experimental Biology·2000

Same author

Pseudotumorous hyperplasia of the caudate lobe in the non-cirrhotic liver: MR and CT arterial portography appearance.

Hepato-gastroenterology·2000

Same author

"Paper-clip" type triple helix formation by 5'-d-(TC)3Ta(CT)3Cb(AG)3 (a and b = 0-4) as a function of loop size with and without the pseudoisocytosine base in the Hoogsteen strand.

Biochemistry·2000

Same author

Acoustic emissions generated in aged dental composites using a laser thermoacoustic technique.

Journal of oral rehabilitation·2000

Same author

Proteolytic activity of cysteine protease in excretory-secretory product of Paragonimus westermani newly excysted metacercariae pivotally regulates IL-8 production of human eosinophils.

Parasite immunology·2000

Same author

Renal infarction in a patient with von Willebrand disease.

Nephrology, dialysis, transplantation : official publication of the European Dialysis and Transplant Association - European Renal Association·2000

Area of Science:

Statistics
Biostatistics
Longitudinal Data Analysis

Background:

Generalized estimating equations (GEE) are widely used for longitudinal data.
Liang and Zeger's GEE models assume missing data are missing completely at random (MCAR).
Violating the MCAR assumption can lead to biased results in GEE analyses.

Purpose of the Study:

To develop a simple and practical procedure for testing the MCAR assumption in GEE.
To provide a method for assessing the validity of GEE models when data may not be missing at random.
To enhance the robustness of longitudinal data analysis.

Main Methods:

The paper proposes a new procedure for testing the MCAR assumption.
This method is related to existing procedures, such as those by Park and Davis.

Related Experiment Videos

The focus is on practical implementation and ease of use.

Main Results:

The developed procedure offers a way to empirically check the MCAR assumption.
This testing capability allows researchers to identify potential biases in their GEE models.
The method aims to improve the trustworthiness of findings from longitudinal studies.

Conclusions:

The proposed procedure is a valuable tool for researchers analyzing longitudinal data.
It helps ensure the validity of GEE models by testing the critical MCAR assumption.
This contributes to more accurate and reliable statistical inferences in longitudinal studies.