A0319
Title: Model based clustering of time-dependent observations with common historical shocks
Authors: Andrea Ongaro - University of Milano-Bicocca (Italy)
Riccardo Corradin - University of Nottingham (United Kingdom)
Luca Danese - University of Milano-Bicocca (Italy) [presenting]
Wasiur Rahman KhudaBukhsh - University of Nottingham (United Kingdom)
Abstract: A novel model-based clustering approach is proposed for samples of time series. A unique commonality is assumed that two observations belong to the same group if structural changes in their behaviors happen at the same time. A latent representation of structural changes is resorted to in each time series based on random orders to induce ties among different observations. Such a general approach can be combined with many time-dependent models known in the literature. The motivation is the epidemiological problem, where the aim is to provide clusters of different countries of the European Union, where two countries belong to the same cluster if the diffusion processes of the COVID-19 virus had structural changes at the same time.
