Online Program Home
  My Program

Abstract Details

Activity Number: 251 - SPEED: Biometrics
Type: Contributed
Date/Time: Monday, July 31, 2017 : 2:00 PM to 2:45 PM
Sponsor: Biometrics Section
Abstract #325160
Title: Smoothing Splines Approach for Longitudinal Analysis of Functional Outcomes
Author(s): Kush Kapur* and Rajesh Selukar and Basil Darras and Seward Rutkove
Companies: Boston Children's Hospital, Harvard Medical School and SAS Institute Inc and Boston Children's Hospital, Harvard Medical School and Beth Israel Deaconess Medical Center, Harvard Medical School
Keywords: smoothing splines ; functional data ; mixed-effects models ; state-space approach ; Kalman filtering and smoothing
Abstract:

In this talk, we propose a functional mixed-effects model using a smoothing spline approach to model functional response at each visit while taking into account of with-in subject correlations of these curves along the longitudinal measurements. Our proposed state space modeling approach allows to differentiate the longitudinal changes in the smooth functional response of underlying populations and provides estimates of the subject and subject-time specific deviations from the population-averaged response curves. We use the precision estimates of the functional effects to construct component-wise Bayesian confidence bands which provide a systematic approach for understanding the underlying uncertainty with the "across-the-function" coverage property. We illustrate our approach on electrical impedance myography data that is being assessed to measure the progression of Duchenne muscular dystrophy non-invasively.


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

Back to the full JSM 2017 program

 
 
Copyright © American Statistical Association