|
Activity Number:
|
11
- Recent Advances in Statistical Methods for Large-Scale Complex Biomedical Data
|
|
Type:
|
Invited
|
|
Date/Time:
|
Sunday, July 28, 2019 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Statistics in Epidemiology
|
|
Abstract #300492
|
|
|
Title:
|
Globally Adaptive Quantile Regression for Complex High-Dimensional Longitudinal Data
|
|
Author(s):
|
Limin Peng* and Huijuan Ma and Qi Zheng and Zhumin Zhang and HuiChuan Lai
|
|
Companies:
|
Emory University and East China Normal University and University of Louisville and University of Wisconsin-Madison and University of Wisconsin-Madison
|
|
Keywords:
|
Association ;
Longitudinal studies;
High-dimensional data;
Globally adaptive quantile regression
|
|
Abstract:
|
Assessing the associations between high-dimensional longitudinal biomarkers and longitudinal outcomes is often of scientific interest but often faces many challenges in real biomedical studies. The data complications include the high-dimensionality, skewness, incompleteness, and constraint of biomarkers along with the longitudinal nature of both biomarkers and outcomes. In this work, we develop a flexible generalization of the recently proposed globally adaptive quantile regression framework to address such complex data scenarios. We develop efficient algorithm to solve the proposed estimation and inference procedures. The proposals are evaluated via extensive simulation studies and an application to a prospective observational dataset.
|
Authors who are presenting talks have a * after their name.
