A signature-based spatial scan statistic for functional data

TL;DR

This paper introduces SigFSS, a novel signature-based spatial scan statistic for functional data, which improves cluster detection accuracy in geographic health data analysis.

Contribution

The paper presents a new spatial scan statistic for functional data that outperforms existing methods in simulations and real-world applications.

Findings

SigFSS outperforms existing approaches in simulations.

SigFSS detects more precise geographic clusters.

Applied to mortality data in France, SigFSS identified significant spatial clusters.

Abstract

We have developed a new signature-based spatial scan statistic for functional data (SigFSS). This scan statistic can be applied to both univariate and multivariate functional data. In a simulation study, SigFSS almost always performed better than the literature approaches and yielded more precise clusters in geographic terms. Lastly, we used SigFSS to search for spatial clusters of abnormally high or abnormally low mortality rates in mainland France.