|
 
|
[GS15a] The effect of missing visits on GEE, a simulation study
Conférence Internationale avec comité de lecture : ASMDA 2015, July 2015, pp.269-276, Piraeus, Greece,Mots clés: Longitudinal data, repeated correlated data, correlation, missing data, simulations, Generalized Estimating Equation
Résumé:
Clinical research is often interested in longitudinal follow-up over several
visits. All scheduled visits are not carried out and it is not unusual to have a diferent
number of visits by patient. The Generalized Estimating Equations can handle con-
tinuous or discrete autocorrelated response. The method allows a diferent number
of visits by patients. The GEE are robust to missing completely at random data, but
when the last visits are fewer, the estimator may be biased. We propose a simula-
tion study to investigate the impact of missing visits on the estimators of the model
parameters under diferent missing data pattern. Diferent types of responses are
studied with an exchangeable or autoregressive of order one structure. The number
of subjects afected by the missing data and the number of visits removed vary in
order to assess the impact of the missing data. Our simulations show that the esti-
mators obtained by GEE are resistant to a certain rate of missing data. The results
are homogeneous regardless to the imposed missing data structure.
Keywords: Longitudinal data, repeated correlated data, correlation,
Commentaires:
The 16th Conference of the Applied Stochastic Models and Data Analysis International Society
Equipe:
msdma
BibTeX
| @inproceedings { | |||
| GS15a, | |||
| title | = | "{ The effect of missing visits on GEE, a simulation study}", | |
| author | = | " J. Geronimi and G. Saporta ", | |
| booktitle | = | "{ASMDA 2015}", | |
| year | = | 2015, | |
| month | = | "July", | |
| pages | = | "269-276", | |
| address | = | "Piraeus, Greece", | |
| note | = | "{The 16th Conference of the Applied Stochastic Models and Data Analysis International Society}", | |
| } | |||
