Publications des scientifiques de l'IRD

Mbougua J. B. T., Laurent Christian, Ndoye I., Delaporte Eric, Gwet H., Molinari N. (2013). Nonlinear multiple imputation for continuous covariate within semiparametric Cox model : application to HIV data in Senegal. Statistics in Medicine, 32 (26), p. 4651-4665. ISSN 0277-6715.

Titre du document
Nonlinear multiple imputation for continuous covariate within semiparametric Cox model : application to HIV data in Senegal
Année de publication
2013
Type de document
Article référencé dans le Web of Science WOS:000325477300012
Auteurs
Mbougua J. B. T., Laurent Christian, Ndoye I., Delaporte Eric, Gwet H., Molinari N.
Source
Statistics in Medicine, 2013, 32 (26), p. 4651-4665 ISSN 0277-6715
Multiple imputation is commonly used to impute missing covariate in Cox semiparametric regression setting. It is to fill each missing data with more plausible values, via a Gibbs sampling procedure, specifying an imputation model for each missing variable. This imputation method is implemented in several softwares that offer imputation models steered by the shape of the variable to be imputed, but all these imputation models make an assumption of linearity on covariates effect. However, this assumption is not often verified in practice as the covariates can have a nonlinear effect. Such a linear assumption can lead to a misleading conclusion because imputation model should be constructed to reflect the true distributional relationship between the missing values and the observed values. To estimate nonlinear effects of continuous time invariant covariates in imputation model, we propose a method based on B-splines function. To assess the performance of this method, we conducted a simulation study, where we compared the multiple imputation method using Bayesian splines imputation model with multiple imputation using Bayesian linear imputation model in survival analysis setting. We evaluated the proposed method on the motivated data set collected in HIV-infected patients enrolled in an observational cohort study in Senegal, which contains several incomplete variables. We found that our method performs well to estimate hazard ratio compared with the linear imputation methods, when data are missing completely at random, or missing at random.
Plan de classement
Sciences fondamentales / Techniques d'analyse et de recherche [020] ; Entomologie médicale / Parasitologie / Virologie [052]
Description Géographique
SENEGAL
Localisation
Fonds IRD [F B010061193]
Identifiant IRD
fdi:010061193
Contact