Change-Point Detection With Multivariate Repeated Measures

TL;DR

This paper introduces a novel graph-based change-point detection method that effectively utilizes both within-individual and between-individual information in multivariate repeated measures data, improving detection accuracy in high-dimensional settings.

Contribution

The paper proposes a new graph-based approach for change-point detection in data with repeated measures, addressing limitations of averaging and incorporating local structures.

Findings

Effective detection of change-points with within-individual differences

Analytical p-value approximations enable efficient significance testing

Successful application to NYC taxi dataset demonstrates practical utility

Abstract

Graph-based methods have shown particular strengths in change-point detection (CPD) tasks for high-dimensional nonparametric settings. However, existing CPD research has rarely addressed data with repeated measurements or local group structures. A common treatment is to average repeated measurements, which can result in the loss of important within-individual information. In this paper, we propose a new graph-based method for detecting change-points in data with repeated measurements or local structures by incorporating both within-individual and between-individual information. Analytical approximations to the significance of the proposed statistics are derived, enabling efficient computation of p-values for the combined test statistic. The proposed method effectively detects change-points across a wide range of alternatives, particularly when within-individual differences are present. The new method is illustrated through an analysis of the New York City taxi dataset.