A spatial scan statistical for categorical, functional data

TL;DR

This paper introduces a new spatial scan statistic for categorical, functional data that effectively detects spatial clusters with high accuracy, low false positives, and is validated through simulations and real air pollution data analysis.

Contribution

The paper presents a novel methodology combining an encoding scheme with a nonparametric scan statistic for spatial clustering of categorical, functional data.

Findings

Accurately recovered simulated spatial clusters

Achieved low false positive and high true positive rates

Successfully identified clusters in French air pollution data

Abstract

We have developed and tested a spatial scan statistic for categorical, functional data (CFSS) - a data structure within which current approaches cannot identify spatial clusters. Our methodology combines an encoding scheme for categorical, functional observations with a nonparametric scan statistic. In a simulation study with three distinct scenarios, the CFSS accurately recovered the simulated spatial clusters and gave very low false positive rates, high true positive rates, and high positive predictive values. We have also used the CFSS to identify and characterize spatial clusters in French air pollution data from the winter of 2024.