|
Activity Number:
|
230
- Longitudinal Data Analysis
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, July 31, 2017 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Biometrics Section
|
|
Abstract #323451
|
|
|
Title:
|
Flexible Models for Multivariate Longitudinal Data Using Copula
|
|
Author(s):
|
Zhentao Tong* and Sujit K Ghosh
|
|
Companies:
|
North Carolina State University and North Carolina State University
|
|
Keywords:
|
copula ;
longitudinal data ;
karhunen-loeve expansion
|
|
Abstract:
|
Analysis of longitudinal data within a mixed effects model framework often are based on stringent parametric assumptions that are often too restrictive in practice. A majority of the currently available models and associated estimation methodologies are based on restrictive assumptions on the correlation structure of longitudinal data, especially when the responses are multivariate vectors consisting of continuous and discrete valued components. This paper proposes a flexible class of models for multivariate longitudinal data based Karhunen-Loeve expansion (KLE) where the zero mean unit variance uncorrelated scores of the KLE are modeled using a restricted version copulas that maintains the moments restrictions. For simplicity of illustration of the proposed models and associated inference, this talk presents only the bivariate case using both real and simulated data scenarios.
|
Authors who are presenting talks have a * after their name.
