Online Program Home
My Program

Abstract Details

Activity Number: 254 - Contributed Poster Presentations: Section on Bayesian Statistical Science
Type: Contributed
Date/Time: Monday, July 29, 2019 : 2:00 PM to 3:50 PM
Sponsor: Section on Bayesian Statistical Science
Abstract #304272
Title: Function Estimation Through Phase and Amplitude Separation
Author(s): James Matuk* and Sebastian Kurtek and Oksana Chkrebtii and Karthik Bharath
Companies: The Ohio State University and The Ohio State University and The Ohio State University and University of Nottingham
Keywords: Functional Data Analysis; Empirical Bayes

An important task in functional data analysis is to estimate a smooth function based on sparse and noisy observations on a time interval. A specific form of sparsity may be introduced during data collection due to occlusions or dropouts where an entire segment of a function is missing. To address this problem, we define a Bayesian model that can fit individual functions on a per subject basis, as well as multiple functions simultaneously by borrowing information across subjects. A distinguishing property of this work is that our model considers amplitude and phase variabilities separately which describe y-axis and x-axis variability, respectively. For this purpose, we use the square-root velocity representation of functions. For the multiple function estimation problem, we assume a common low-dimensional template function to model amplitude and use subject-specific warping functions to model phase. This setup allows these fitted functions to share common features while allowing uncertainty quantification in terms of the two components separately. We validate the proposed framework using multiple simulated examples as well as real data including ECG signals and growth curves.

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

Back to the full JSM 2019 program