Activity Number:
|
531
- SPEED: Statistics in Epidemiology and Genomics and Genetics
|
Type:
|
Contributed
|
Date/Time:
|
Wednesday, August 2, 2017 : 11:35 AM to 12:20 PM
|
Sponsor:
|
Section on Statistics in Genomics and Genetics
|
Abstract #325394
|
|
Title:
|
Association Study of Children's Methylation and Growth Trajectory Using Functional Mixed Models
|
Author(s):
|
Colleen McKendry* and Arnab Maity and Jung-Ying Tzeng
|
Companies:
|
North Carolina State University and North Carolina State University and North Carolina State University
|
Keywords:
|
functional data ;
gaussian process ;
growth trajectory
|
Abstract:
|
This paper is motivated by the Newborn Epigenetic STudy (NEST) data. We consider the problem of associating children growth trajectory and children gene methylation profile while accounting for other confounders. A functional semiparametric regression modeling framework is developed, where the response is functional (children growth trajectory measured over time) and the covariates are both scalar and vector values (gene methylation profile and other confounders). We model the joint effect of the gene methylation profile nonparametrically using the Gaussian process framework, and model the remaining confounders parametrically. We develop hypothesis testing procedures for the effect of the gene methylation profiles using functional mixed effects models and variance components. The performance of our method is evaluated through a simulation study and via application to the NEST data.
|
Authors who are presenting talks have a * after their name.