A change-point problem for $m$-dependent multivariate random field

TL;DR

This paper introduces a change-point detection method for multivariate random fields using CUSUM statistics, effectively controlling false positives and family-wise error rates in a multidimensional setting.

Contribution

It proposes a novel change-point test for $m$-dependent multivariate random fields under a distribution-free framework, addressing multiple hypothesis testing issues.

Findings

Effective detection of change-points in multivariate fields

Control of false positive and family-wise error rates

Applicable to high-dimensional spatial data

Abstract

In this paper, we consider a change-point problem for a centered, stationary and $m$-dependent multivariate random field. Under the distribution free assumption, a change-point test using CUSUM statistic is proposed to detect anomalies within a multidimensional random field, controlling the false positive rate as well as the Family-Wise Error in the multiple hypotheses testing context.