The paper “An Autocovariance-Based Learning Framework for High-Dimensional Functional Time Series”, co-authored by Prof. Jinyuan Chang and postdoctoral researcher Cheng Chen from the Joint Laboratory of Data Science and Business Intelligence at Southwestern University of Finance and Economics, in collaboration with Prof. Xinghao Qiao and Prof. Qiwei Yao from the London School of Economics and Political Science, has been officially accepted by the Journal of Econometrics, a leading international journal in the field of econometrics.
Abstract
This paper investigates how to estimate high-dimensional functional time series models of interest based on observations with noise pollution, and proposes a “three-step” framework: firstly, an operator is constructed based on the autocorrelation information of the observation sequence, and the estimation problem of functional parameters in the original model is transformed into a parameter estimation problem in Euclidean space through spectral decomposition of the operator; Then, block regularized minimum distance estimation about unknown parameters in Euclidean space is obtained through autocovariance information; Finally, the obtained estimate will be transformed into an estimate of the functional parameters in the original model through a one-to-one mapping. This article systematically studies the theoretical properties of the proposed method and analyzes the convergence speed of corresponding estimates on three high-dimensional functional time series models: “scalar function regression”, “function function regression”, and “function vector autoregression”. Numerical simulation and case analysis demonstrate the superiority of the proposed method.
Author Introduction
Jinyuan Chang is the Executive Director of the Joint Laboratory of Data Science and Business Intelligence at Southwestern University of Finance and Economics. He is a Guanghua Distinguished Professor, Doctoral Supervisor, recipient of the National Science Fund for Distinguished Young Scholars of China, a Distinguished Expert of Sichuan Province, and a member of the Sichuan Province Statistical Expert Advisory Committee. His research primarily focuses on ultra-high dimensional data analysis and high-frequency financial data analysis.
Cheng Chen is a postdoctoral fellow at the School of Statistics, Southwestern University of Finance and Economics, supervised by Professor Jinyuan Chang. His main research interests include functional data analysis and high-dimensional time series analysis.
Xinghao Qiao is an Associate Professor at the London School of Economics and Political Science. His research areas include functional data analysis, complex time series analysis, high-dimensional statistics, and nonparametric Bayesian analysis.
Qiwei Yao is a Chair Professor at the London School of Economics and Political Science. He is a Fellow of the Institute of Mathematical Statistics, an Elected Member of the International Statistical Institute, and a Fellow of the American Statistical Association. His research focuses on time series analysis, high-dimensional time series modeling and forecasting, dimensionality reduction, factor modeling, dynamic network modeling, spatiotemporal modeling, financial econometrics, and nonparametric regression.
