Recent Developments in Nonstationary Time Series Analysis with Applications

In this talk, I will present recent advances in the analysis of nonstationary time series, covering key aspects such as structural approximation, estimation, prediction, inference, and classification. Additionally, for locally stationary time series, I will discuss how sieve-based methods can be leveraged to achieve fast, adaptive, and rate-optimal results. To illustrate the superior performance of these approaches, I will include both simulation studies and real data analyses. This talk is based on recent joint works with Chen Qian (UC Davis), Li Zhou (UC Davis), Lexin Li (UC Berkeley), and Zhou Zhou (University of Toronto).

Xiucai Ding is currently an assistant professor of statistics at UC Davis. Previously, he was a postdoc in Duke. He obtained his PhD from the University of Toronto. His main research interest includes applied probability methods (random matrix theory, random graph theory and Riemann-Hilbert approach) to high dimensional statistics, manifold learning and deep learning theory, as well as nonstationary time series analysis.

Host: Ran Chen