A geometric approach to visualization of variability in functional data

We propose a new method for the construction and visualization of boxplot-type displays for functional data. We use a recent functional data analysis framework, based on a representation of functions called square-root slope functions, to decompose observed variation in functional data into three ma...

Full description

Bibliographic Details
Main Authors: Xie, Weiyi, Kurtek, Sebastian, Bharath, Karthik, Sun, Ying
Format: Article
Published: Taylor & Francis 2016
Subjects:
Online Access:https://eprints.nottingham.ac.uk/40806/
_version_ 1848796137967845376
author Xie, Weiyi
Kurtek, Sebastian
Bharath, Karthik
Sun, Ying
author_facet Xie, Weiyi
Kurtek, Sebastian
Bharath, Karthik
Sun, Ying
author_sort Xie, Weiyi
building Nottingham Research Data Repository
collection Online Access
description We propose a new method for the construction and visualization of boxplot-type displays for functional data. We use a recent functional data analysis framework, based on a representation of functions called square-root slope functions, to decompose observed variation in functional data into three main components: amplitude, phase, and vertical translation. We then construct separate displays for each component, using the geometry and metric of each representation space, based on a novel definition of the median, the two quartiles, and extreme observations. The outlyingness of functional data is a very complex concept. Thus, we propose to identify outliers based on any of the three main components after decomposition. We provide a variety of visualization tools for the proposed boxplot-type displays including surface plots. We evaluate the proposed method using extensive simulations and then focus our attention on three real data applications including exploratory data analysis of sea surface temperature functions, electrocardiogram functions and growth curves.
first_indexed 2025-11-14T19:43:12Z
format Article
id nottingham-40806
institution University of Nottingham Malaysia Campus
institution_category Local University
last_indexed 2025-11-14T19:43:12Z
publishDate 2016
publisher Taylor & Francis
recordtype eprints
repository_type Digital Repository
spelling nottingham-408062020-05-04T18:25:34Z https://eprints.nottingham.ac.uk/40806/ A geometric approach to visualization of variability in functional data Xie, Weiyi Kurtek, Sebastian Bharath, Karthik Sun, Ying We propose a new method for the construction and visualization of boxplot-type displays for functional data. We use a recent functional data analysis framework, based on a representation of functions called square-root slope functions, to decompose observed variation in functional data into three main components: amplitude, phase, and vertical translation. We then construct separate displays for each component, using the geometry and metric of each representation space, based on a novel definition of the median, the two quartiles, and extreme observations. The outlyingness of functional data is a very complex concept. Thus, we propose to identify outliers based on any of the three main components after decomposition. We provide a variety of visualization tools for the proposed boxplot-type displays including surface plots. We evaluate the proposed method using extensive simulations and then focus our attention on three real data applications including exploratory data analysis of sea surface temperature functions, electrocardiogram functions and growth curves. Taylor & Francis 2016-12-16 Article PeerReviewed Xie, Weiyi, Kurtek, Sebastian, Bharath, Karthik and Sun, Ying (2016) A geometric approach to visualization of variability in functional data. Journal of the American Statistical Association, 112 (519). pp. 979-993. ISSN 1537-274X Amplitude and phase variabilities Fisher–Rao metric Functional outlier detection Square-root slope function http://dx.doi.org/10.1080/01621459.2016.1256813 doi:10.1080/01621459.2016.1256813 doi:10.1080/01621459.2016.1256813
spellingShingle Amplitude and phase variabilities
Fisher–Rao metric
Functional outlier detection
Square-root slope function
Xie, Weiyi
Kurtek, Sebastian
Bharath, Karthik
Sun, Ying
A geometric approach to visualization of variability in functional data
title A geometric approach to visualization of variability in functional data
title_full A geometric approach to visualization of variability in functional data
title_fullStr A geometric approach to visualization of variability in functional data
title_full_unstemmed A geometric approach to visualization of variability in functional data
title_short A geometric approach to visualization of variability in functional data
title_sort geometric approach to visualization of variability in functional data
topic Amplitude and phase variabilities
Fisher–Rao metric
Functional outlier detection
Square-root slope function
url https://eprints.nottingham.ac.uk/40806/
https://eprints.nottingham.ac.uk/40806/
https://eprints.nottingham.ac.uk/40806/