|
Activity Number:
|
140
- Change-Points in Multivariate and High-Dimensional Data
|
|
Type:
|
Invited
|
|
Date/Time:
|
Tuesday, August 10, 2021 : 10:00 AM to 11:50 AM
|
|
Sponsor:
|
Section on Nonparametric Statistics
|
|
Abstract #314426
|
|
|
Title:
|
Inference for a Change Point in High-Dimensional Data via Self-Normalization
|
|
Author(s):
|
Runmin Wang and Changbo Zhu and Stanislav Volgushev and Xiaofeng Shao*
|
|
Companies:
|
Southern Methodist University and University of California, Davis and University of Toronto and University of Illinois at Urbana-Champaign
|
|
Keywords:
|
U Statistics;
Segmentation;
Time Series;
Structural Break
|
|
Abstract:
|
In this talk, I will present some recent work on change point testing and estimation for high-dimensional data. For testing a mean shift in the independent high-dimensional data, we propose a new test which is based on U-statistics and utilizes the self-normalization principle. Our test targets dense alternatives in the high-dimensional setting and involves no tuning parameters. We show the weak convergence of a sequential U-statistic based process to derive the pivotal limit under the null and also obtain the asymptotic power under the local alternatives. An extension to high dimensional time series will also be presented with rigorous asymptotic theory and encouraging simulation results. If time permits, I will describe how our approach can be used in combination with wild binary segmentation to estimate the number and location of multiple unknown change points.
|
Authors who are presenting talks have a * after their name.
