Online Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 264 - New Statistical Methods for Longitudinal Data Analysis
Type: Topic Contributed
Date/Time: Tuesday, August 4, 2020 : 1:00 PM to 2:50 PM
Sponsor: International Chinese Statistical Association
Abstract #311012
Title: Multivariate Partial Linear Varying-Coefficient Model for G×E Studies with Longitudinal Traits
Author(s): Yuehua Cui*
Companies: Michigan State University
Keywords: gene-environment interaction; multiple longitudinal traits; quadratic inference function; penalized spline; pleiotropy
Abstract:

For many complex diseases, multiple phenotypic measurements can be used to quantify the disease status. Such correlated phenotypes often share common genetic determinants. For multivariate longitudinal data, when multiple response variables are jointly measured over time, the correlation information between multivariate longitudinal responses can be taken into account to identify pleotropic effects. In this work, we proposed a multivariate partially linear varying coefficients model to identify genetic variants with their effects nonlinearly modified by environmental factors over time. We derived a testing framework to jointly test the association of genetic factors with a bivariate phenotypic trait. We extended the quadratic inference functions to deal with the longitudinal correlations and used penalized splines for the approximation of nonparametric coefficients, and further showed the consistency and asymptotic normality of the estimates. The performance of the testing procedure was evaluated through Monte Carlo simulation studies. The utility of the method was further demonstrated through a real data analysis.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2020 program