JSM 2015 Preliminary Program

Online Program Home
My Program

Abstract Details

Activity Number: 327
Type: Invited
Date/Time: Tuesday, August 11, 2015 : 10:30 AM to 12:20 PM
Sponsor: Biometrics Section
Abstract #314187 View Presentation
Title: Regression Analysis of Longitudinal Networked Data
Author(s): Peter X.K. Song* and Yan Zhou
Companies: University of Michigan and University of Michigan
Keywords: estimating function ; neuroimaging ; prior network topology ; tuning
Abstract:

Longitudinal networked data refer to repeated measurements collected from units/subjects over time from a network. Such data arise frequently from studies in social and health sciences. We develop a new methodology to account for both within-subject and network-level correlations in the context of marginal models for continuous and discrete outcomes. To incorporate both prior network topology and data-driven network-level correlation into the regression analysis, we propose a hybrid estimating function approach for statistical estimation and inference. Moreover, a Godambe information based tuning strategy is proposed to allocate hybrid weights so that the resulting estimation achieves optimal efficiency. A clear advantage of the proposed estimation method is its computation feasibility. Also, it has desirable large-sample properties in both estimation and inference. The proposed estimation method is evaluated through simulation studies and illustrated by a real example of neuroimaging data concerning an association study of iron deficiency on infant's auditory recognition memory.


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

Back to the full JSM 2015 program





For program information, contact the JSM Registration Department or phone (888) 231-3473.

For Professional Development information, contact the Education Department.

The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.

2015 JSM Online Program Home