Conference Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 118 - Recent Advances in Change-Point Analysis
Type: Invited
Date/Time: Monday, August 8, 2022 : 10:30 AM to 12:20 PM
Sponsor: Section on Nonparametric Statistics
Abstract #320635
Title: Nonparametric Online Change-Point Detection in High Dimensions
Author(s): Ali Shojaie*
Companies: University of Washington
Keywords:
Abstract:

Online change-point detection arises naturally in analysis of sequentially observed data. Recently proposed methods for high-dimensional online change-point detection primarily focus on detecting changes in means or covariance matrices and do not account for more general changes in the data distribution. To bridge this gap, we propose a nonparametric online change-point detection methods for high-dimensional problems based on the extension of energy statistic. We investigate asymptotic properties of the proposed estimator and demonstrate the method using simulated and real data examples.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2022 program