{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T17:04:23Z","timestamp":1792256663296,"version":"4.4.0"},"reference-count":37,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T00:00:00Z","timestamp":1748563200000},"content-version":"vor","delay-in-days":149,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,21]]},"abstract":"<jats:title>Summary<\/jats:title>\n                  <jats:p>Functional data analysis offers a diverse toolkit of statistical methods tailored to analysing samples of real-valued random functions. Recently, samples of time-varying random objects, such as time-varying networks, have been increasingly encountered in data analysis. These data structures represent elements within general metric spaces that lack local or global linear structures, rendering traditional functional data analysis methods inapplicable. Moreover, the existing methodology for time-varying random objects does not work well in the presence of outlying objects. In this article, we propose a robust method for analysing time-varying random objects. Our method employs pointwise Fr\u00e9chet medians and constructs pointwise distance trajectories between the individual sample functions and the sample Fr\u00e9chet median curve. This representation effectively transforms time-varying objects into functional data. A novel robust approach to functional principal component analysis, based on a Winsorized $ U $-statistic estimator of the covariance structure, is introduced. The proposed robust analysis of these distance trajectories is able to identify key features of object trajectories over time and is useful for downstream analysis. One contribution of this work is to provide a theoretical basis for establishing the asymptotic equicontinuity of time-varying $ M $-estimators located in a general metric space. To illustrate the efficacy of our approach, numerical studies focusing on dynamic networks and time-varying spherical data are conducted. The results indicate that the proposed method exhibits good all-round performance and surpasses existing approaches in terms of robustness, showcasing its superior performance in handling time-varying object data.<\/jats:p>","DOI":"10.1093\/biomet\/asaf040","type":"journal-article","created":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T07:43:05Z","timestamp":1748504585000},"source":"Crossref","is-referenced-by-count":1,"title":["Robust functional principal component analysis for non-Euclidean random objects"],"prefix":"10.1093","volume":"112","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-7870-0340","authenticated-orcid":false,"given":"Jiazhen","family":"Xu","sequence":"first","affiliation":[{"name":"Research School of Finance, Actuarial Studies and Statistics, Australian National University , Building 26C Kingsley Street , Canberra, Australian Capital Territory 2600,","place":["Australia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew T A","family":"Wood","sequence":"additional","affiliation":[{"name":"Research School of Finance, Actuarial Studies and Statistics, Australian National University , Building 26C Kingsley Street , Canberra, Australian Capital Territory 2600,","place":["Australia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7415-908X","authenticated-orcid":false,"given":"Tao","family":"Zou","sequence":"additional","affiliation":[{"name":"Research School of Finance, Actuarial Studies and Statistics, Australian National University , Building 26C Kingsley Street , Canberra, Australian Capital Territory 2600,","place":["Australia"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,5,30]]},"reference":[{"key":"2026032607101281100_asaf040-B1","doi-asserted-by":"crossref","first-page":"348","DOI":"10.1016\/j.joems.2015.10.003","article-title":"A convexity of functions on convex metric spaces of Takahashi and applications","volume":"24","author":"Abdelhakim","year":"2016","journal-title":"J. Egyptian Math. Soc"},{"key":"2026032607101281100_asaf040-B2","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1007\/s00440-019-00950-0","article-title":"Convergence rates for empirical barycenters in metric spaces: Curvature, convexity and extendable geodesics","volume":"177","author":"Ahidar-Coutrix","year":"2020","journal-title":"Prob. Theory Rel. Fields"},{"key":"2026032607101281100_asaf040-B3","doi-asserted-by":"crossref","first-page":"1494","DOI":"10.1214\/aop\/1176989128","article-title":"Limit theorems for U-processes","volume":"21","author":"Arcones","year":"1993","journal-title":"Ann. Prob"},{"key":"2026032607101281100_asaf040-B4","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1016\/0304-4149(94)90098-1","article-title":"U-processes indexed by Vapnik-Cervonenkis classes of functions with applications to asymptotics and bootstrap of U-statistics with estimated parameters","volume":"52","author":"Arcones","year":"1994","journal-title":"Stoch. Proces. Applic"},{"key":"2026032607101281100_asaf040-B5","doi-asserted-by":"crossref","first-page":"1858","DOI":"10.1016\/j.spl.2009.05.016","article-title":"Principal points and elliptical distributions from the multivariate setting to the functional case","volume":"79","author":"Bali","year":"2009","journal-title":"Statist. Prob. Lett"},{"key":"2026032607101281100_asaf040-B6","doi-asserted-by":"crossref","first-page":"1573","DOI":"10.1214\/21-AOS2163","article-title":"Uniform convergence of local Fr\u00e9chet regression with applications to locating extrema and time warping for metric space valued trajectories","volume":"50","author":"Chen","year":"2022","journal-title":"Ann. Statist."},{"key":"2026032607101281100_asaf040-B7","doi-asserted-by":"crossref","first-page":"1328","DOI":"10.1111\/biom.13385","article-title":"Modeling sparse longitudinal data on Riemannian manifolds","volume":"77","author":"Dai","year":"2021","journal-title":"Biometrics"},{"key":"2026032607101281100_asaf040-B8","doi-asserted-by":"crossref","first-page":"3334","DOI":"10.1214\/17-AOS1660","article-title":"Principal component analysis for functional data on Riemannian manifolds and spheres","volume":"46","author":"Dai","year":"2018","journal-title":"Ann. Statist."},{"key":"2026032607101281100_asaf040-B9","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1111\/rssb.12337","article-title":"Functional models for time-varying random objects","volume":"82","author":"Dubey","year":"2020","journal-title":"J. R. Statist. Soc. B"},{"key":"2026032607101281100_asaf040-B10","doi-asserted-by":"crossref","first-page":"2252","DOI":"10.1080\/01621459.2021.1917416","article-title":"Modeling time-varying random objects and dynamic networks","volume":"117","author":"Dubey","year":"2021","journal-title":"J. Am. Statist. Assoc"},{"key":"2026032607101281100_asaf040-B11","doi-asserted-by":"crossref","first-page":"587","DOI":"10.1093\/biomet\/asn031","article-title":"Robust functional estimation using the median and spherical principal components","volume":"95","author":"Gervini","year":"2008","journal-title":"Biometrika"},{"key":"2026032607101281100_asaf040-B12","doi-asserted-by":"crossref","first-page":"252","DOI":"10.1080\/01621459.2016.1246366","article-title":"ECA: High-dimensional elliptical component analysis in non-Gaussian distributions","volume":"113","author":"Han","year":"2018","journal-title":"J. Am. Statist. Assoc"},{"key":"2026032607101281100_asaf040-B13","volume-title":"Robust Statistics","author":"Huber","year":"2004"},{"key":"2026032607101281100_asaf040-B14","doi-asserted-by":"crossref","DOI":"10.1002\/9781118762547","volume-title":"Theoretical Foundations of Functional Data Analysis, with an Introduction to Linear Operators","author":"Hsing","year":"2015"},{"key":"2026032607101281100_asaf040-B15","volume-title":"An Introduction to Metric Spaces and Fixed Point Theory","author":"Khamsi","year":"2011"},{"key":"2026032607101281100_asaf040-B16","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1214\/09-AOAS308","article-title":"Estimating time-varying networks","volume":"4","author":"Kolar","year":"2010","journal-title":"Ann. Appl. Statist"},{"key":"2026032607101281100_asaf040-B17","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1007\/s11222-024-10413-9","article-title":"Generalized spherical principal component analysis","volume":"34","author":"Leyder","year":"2024","journal-title":"Statist. Comp"},{"key":"2026032607101281100_asaf040-B18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/BF02595862","article-title":"Robust principal component analysis for functional data (with Discussion)","volume":"8","author":"Locantore","year":"1999","journal-title":"Test"},{"key":"2026032607101281100_asaf040-B19","doi-asserted-by":"crossref","first-page":"349","DOI":"10.1016\/S0167-7152(98)00272-7","article-title":"Some robust estimates of principal components","volume":"43","author":"Marden","year":"1999","journal-title":"Statist. Prob. Lett"},{"key":"2026032607101281100_asaf040-B20","doi-asserted-by":"crossref","DOI":"10.1201\/9781351189675","volume-title":"Object Oriented Data Analysis","author":"Marron","year":"2021"},{"key":"2026032607101281100_asaf040-B21","doi-asserted-by":"crossref","first-page":"691","DOI":"10.1214\/17-AOS1624","article-title":"Fr\u00e9chet regression for random objects with Euclidean predictors","volume":"47","author":"Petersen","year":"2019","journal-title":"Ann. Statist."},{"key":"2026032607101281100_asaf040-B22","doi-asserted-by":"crossref","first-page":"462","DOI":"10.1214\/aos\/1176345787","article-title":"On the asymptotic normality of statistics with estimated parameters","volume":"10","author":"Randles","year":"1982","journal-title":"Ann. Statist."},{"key":"2026032607101281100_asaf040-B23","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1016\/j.jmva.2018.11.010","article-title":"A generalized spatial sign covariance matrix","volume":"171","author":"Raymaekers","year":"2019","journal-title":"J. Mult. Anal"},{"key":"2026032607101281100_asaf040-B24","article-title":"Learning spatiotemporal trajectories from manifold-valued longitudinal data","author":"Schiratti","year":"2015","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2026032607101281100_asaf040-B25","doi-asserted-by":"crossref","first-page":"1696","DOI":"10.1214\/22-AOS2172","article-title":"Intrinsic Riemannian functional data analysis for sparse longitudinal observations","volume":"50","author":"Shao","year":"2022","journal-title":"Ann. Statist."},{"key":"2026032607101281100_asaf040-B26","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4939-4020-2","volume-title":"Functional and Shape Data Analysis","author":"Srivastava","year":"2016"},{"key":"2026032607101281100_asaf040-B27","first-page":"338","volume-title":"Heat Kernels and Analysis on Manifolds, Graphs & Metric Spaces: Lecture Notes from a Quarter Program on Heat Kernels, Random Walks, and Analysis on Manifolds and Graphs, April 16\u2013July 13, 2002, Emile Borel Centre of the Henri Poincar\u00e9 Institute, Paris, France","author":"Sturm","year":"2003"},{"key":"2026032607101281100_asaf040-B28","doi-asserted-by":"crossref","first-page":"765","DOI":"10.1016\/j.spl.2012.01.001","article-title":"Robustifying principal component analysis with spatial sign vectors","volume":"82","author":"Taskinen","year":"2012","journal-title":"Statist. Prob. Lett"},{"key":"2026032607101281100_asaf040-B29","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511802256","volume-title":"Asymptotic Statistics","author":"van der Vaart","year":"1998"},{"key":"2026032607101281100_asaf040-B30","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-2545-2","volume-title":"Weak Convergence of Empirical Processes: With Applications to Statistics","author":"van der Vaart","year":"1996"},{"key":"2026032607101281100_asaf040-B31","doi-asserted-by":"crossref","first-page":"557","DOI":"10.1016\/S0378-3758(00)00199-3","article-title":"Sign and rank covariance matrices","volume":"91","author":"Visuri","year":"2000","journal-title":"J. Statist. Plan. Infer"},{"key":"2026032607101281100_asaf040-B32","doi-asserted-by":"crossref","DOI":"10.1017\/9781108627771","volume-title":"High-Dimensional Statistics: A Non-Asymptotic Viewpoint","author":"Wainwright","year":"2019"},{"key":"2026032607101281100_asaf040-B33","doi-asserted-by":"crossref","first-page":"1239","DOI":"10.1111\/biom.13695","article-title":"Robust functional principal component analysis via a functional pairwise spatial sign operator","volume":"79","author":"Wang","year":"2023","journal-title":"Biometrics"},{"key":"2026032607101281100_asaf040-B34","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1146\/annurev-statistics-041715-033624","article-title":"Functional data analysis","volume":"3","author":"Wang","year":"2016","journal-title":"Ann. Rev. Statist. Appl"},{"key":"2026032607101281100_asaf040-B35","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1006\/nimg.2001.0933","article-title":"A general statistical analysis for fMRI data","volume":"15","author":"Worsley","year":"2002","journal-title":"Neuroimage"},{"key":"2026032607101281100_asaf040-B36","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11749-023-00876-9","article-title":"Shape-based functional data analysis","volume":"33","author":"Wu","year":"2024","journal-title":"Test"},{"key":"2026032607101281100_asaf040-B37","doi-asserted-by":"crossref","first-page":"104864","DOI":"10.1016\/j.jmva.2021.104864","article-title":"Robust functional principal component analysis for non-Gaussian longitudinal data","volume":"189","author":"Zhong","year":"2022","journal-title":"J. Mult. Anal"}],"container-title":["Biometrika"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/biomet\/advance-article-pdf\/doi\/10.1093\/biomet\/asaf040\/63406942\/asaf040.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/biomet\/article-pdf\/112\/4\/asaf040\/63406942\/asaf040.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/biomet\/article-pdf\/112\/4\/asaf040\/63406942\/asaf040.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T11:10:21Z","timestamp":1774523421000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/biomet\/article\/doi\/10.1093\/biomet\/asaf040\/8153903"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":37,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,10,21]]}},"URL":"https:\/\/doi.org\/10.1093\/biomet\/asaf040","relation":{},"ISSN":["1464-3510"],"issn-type":[{"value":"1464-3510","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025]]},"published":{"date-parts":[[2025]]},"article-number":"asaf040"}}