A0230
Title: Multivariate contaminated normal linear mixed models with application to longitudinal Alzheimer's disease data
Authors: Wan-Lun Wang - National Cheng Kung University (Taiwan) [presenting]
Tsung-I Lin - National Chung Hsing University (Taiwan)
Abstract: A robust approach is proposed to jointly modeling multiple repeated clinical measures with intricate features. More specifically, the aim is to expand the scope of the multivariate linear mixed model by using the multivariate contaminated normal distribution. The proposed model called the MCNLMM-CM, is designed to handle minor outliers effectively while simultaneously accommodating censored measurements and intermittent missing responses. An expectation conditional maximization (ECME) algorithm is developed to estimate the parameters of the proposed model in situations involving missing at-random responses. Techniques for approximating the asymptotic standard errors of model parameters are also provided, recovering censored data, imputing missing values, and identifying outliers. The proposed methodology is inspired by and applied to data from the Alzheimer's Disease Neuroimaging Initiative cohort study, which involves longitudinal clinical measurements of patients with mild cognitive impairment. A simulation study is conducted to evaluate the finite-sample properties of the parameter estimators.
