Spatio-temporal hierarchical clustering of interval time series  with application to suicide rates in Europe

Raffaele Mattera; Philip Hans Franses

Conferences CIMPA, 18th International Federation of Classification Societies

Spatio-temporal hierarchical clustering of interval time series with application to suicide rates in Europe

Raffaele Mattera, Philip Hans Franses

Last modified: 2024-05-14

Abstract

In this paper we investigate similarities of suicide rates in Europe, which are available as interval time series. For this aim, a novel spatio-temporal hierarchical clustering algorithm for interval time series data is proposed. The spatial dimension is included in the clustering process to account for possible relevant information such as weather conditions, sunlight hours and socio-cultural factors. Our results indicate the presence of six main clusters in Europe, which almost overlap with the sunlight hours distribution. Differences between male and female suicide rates are also investigated.

Keywords

symbolic data analysis, spatio-temporal modelling, spatial data science

References

Chavent, M., Kuentz-Simonet, V., Labenne, A., & Saracco, J. (2018). ClustGeo: an R package for hierarchical clustering with spatial constraints. Computational Statistics, 33(4), 1799-1822.Mattera, R., & Franses, P. H. (2023). Are African business cycles synchronized? Evidence from spatio-temporal modeling. Economic Modelling, 128, 106485.Maharaj, E. A., Teles, P., & Brito, P. (2019). Clustering of interval time series. Statistics and Computing, 29, 1011-1034.