Advances and Applications in Statistics
Volume 64, Issue 2, Pages 127 - 142
(October 2020) http://dx.doi.org/10.17654/AS064020127 |
|
FITTING LONGITUDINAL DATA WITH MISSING VALUES IN THE RESPONSE AND COVARIATES
Nesma M. Darwish, Ahmed M. Gad and Ramadan H. Mohamed
|
Abstract: Longitudinal data are not uncommon in many disciplines where repeated measurements on a response variable are collected for all subjects. Dropout pattern occurs when some subjects leave the study prematurely results in missing values in the response variable. The missing data may also exist in covariates. The missing data mechanism is termed as non-random when the probability of missingness depends on the missing value, and may be on the observed values. Ignoring the missing values in this case leads to biased inference. In this article, a multiple imputation approach is suggested to handle missing values in the responses and covariates. The shared parameter model is used to fit longitudinal data in the presence of non-random dropout. The stochastic EM algorithm is developed to obtain the model parameter estimates including missingness parameters. Standard errors of estimates have been calculated using the developed Monte Carlo method. The performance of the proposed approach is evaluated through a simulation study. Also, the proposed approach is applied to a real data set. |
Keywords and phrases: dropout, longitudinal data, missing covariates, multiple imputations, shared parameters, stochastic EM algorithm.
|
|
Number of Downloads: 246 | Number of Views: 539 |
|