Graphical Principal Component Analysis of Multivariate Functional Time Series

被引:1
|
作者
Tan, Jianbin [1 ]
Liang, Decai [2 ]
Guan, Yongtao [3 ]
Huang, Hui [4 ,5 ]
机构
[1] Sun Yat Sen Univ, Sch Math, Guangzhou, Peoples R China
[2] Nankai Univ, Sch Stat & Data Sci, LPMC & KLMDASR, Tianjin, Peoples R China
[3] Chinese Univ Hong Kong, Shenzhen Res Inst Big Data, Sch Data Sci, Shenzhen, Peoples R China
[4] Renmin Univ China, Ctr Appl Stat, Beijing, Peoples R China
[5] Renmin Univ China, Sch Stat, Beijing, Peoples R China
基金
中国国家自然科学基金;
关键词
Dynamic functional principal component analysis; Functional time series; Graphical model; Weak separability; Whittle likelihood; MODELS; THEOREM; LASSO;
D O I
10.1080/01621459.2024.2302198
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
In this article, we consider multivariate functional time series with a two-way dependence structure: a serial dependence across time points and a graphical interaction among the multiple functions within each time point. We develop the notion of dynamic weak separability, a more general condition than those assumed in literature, and use it to characterize the two-way structure in multivariate functional time series. Based on the proposed weak separability, we develop a unified framework for functional graphical models and dynamic principal component analysis, and further extend it to optimally reconstruct signals from contaminated functional data using graphical-level information. We investigate asymptotic properties of the resulting estimators and illustrate the effectiveness of our proposed approach through extensive simulations. We apply our method to hourly air pollution data that were collected from a monitoring network in China. Supplementary materials for this article are available online.
引用
收藏
页码:3073 / 3085
页数:13
相关论文
共 50 条
  • [31] Principal component analysis for multivariate extremes
    Drees, Holger
    Sabourin, Anne
    ELECTRONIC JOURNAL OF STATISTICS, 2021, 15 (01): : 908 - 943
  • [32] Multivariate control charts for grade control using principal-component analysis and time-series modelling
    Samanta, B
    TRANSACTIONS OF THE INSTITUTION OF MINING AND METALLURGY SECTION A-MINING TECHNOLOGY, 2002, 111 : A149 - A157
  • [33] Time Series Clustering Method Based on Principal Component Analysis
    Cao, Danyang
    Tian, Yuan
    Bai, Donghui
    PROCEEDINGS OF THE 5TH INTERNATIONAL CONFERENCE ON INFORMATION ENGINEERING FOR MECHANICS AND MATERIALS, 2015, 21 : 888 - 895
  • [34] Symplectic Principal Component Analysis: A New Method for Time Series Analysis
    Lei, Min
    Meng, Guang
    MATHEMATICAL PROBLEMS IN ENGINEERING, 2011, 2011
  • [35] Analysis of principal functional components in economic time series
    Chavez Chong, Cristina O.
    Sanchez Garcia, Jesus E.
    DelaCerda Gastelum, Jose
    GECONTEC-REVISTA INTERNACIONAL DE GESTION DEL CONOCIMIENTO Y LA TECNOLOGIA, 2015, 3 (02): : 13 - 25
  • [36] Competitive principal component analysis for locally stationary time series
    Fancourt, CL
    Principe, JC
    IEEE TRANSACTIONS ON SIGNAL PROCESSING, 1998, 46 (11) : 3068 - 3081
  • [37] Multivariate Functional Principal Component Analysis for Data Observed on Different (Dimensional) Domains
    Happ, Clara
    Greven, Sonja
    JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 2018, 113 (522) : 649 - 659
  • [38] A general framework for multivariate functional principal component analysis of amplitude and phase variation
    Happ, Clara
    Scheipl, Fabian
    Gabriel, Alice-Agnes
    Greven, Sonja
    STAT, 2019, 8 (01):
  • [39] Hierarchical sparse functional principal component analysis for multistage multivariate profile data
    Wang, Kai
    Tsung, Fugee
    IISE TRANSACTIONS, 2021, 53 (01) : 58 - 73
  • [40] Principal response curves technique for the analysis of multivariate biomonitoring time series
    Paul J. van den Brink
    Piet J. den Besten
    Abraham bij de Vaate
    Cajo J. F. ter Braak
    Environmental Monitoring and Assessment, 2009, 152 : 271 - 281