Document type
Bachelor thesisPublication date
Please use this identifier to cite or link to this item: https://hdl.handle.net/2445/214426
Bayesian spatio-temporal analysis of the COVID-19 pandemic in Catalonia
Journal Title
Authors
Director/Tutor
Journal ISSN
Volume Title
Related resource
Abstract
In this study, we model the COVID-19 pandemic in the different basic health areas (ABS) in Catalonia, describing the spatial, temporal and spatio-temporal trends of reported COVID-19 cases and hospitalisations. As the ABS are small areas, spatiotemporal small area estimation methods have to be used, which allow us to borrow strength from neighbouring areas and time points. In particular, we use Bayesian hierarchical spatio-temporal models estimated with INLA, providing a very flexible and robust tool that allows the specification of a wide variety of different models, from which the best one is selected according to the model performance. Results are found to be heterogeneous and different hotspots and coldspots are identified both over the whole pandemic period and at different points in time. The analysis of the impact of some characteristics of the ABS shows that urban areas are at higher risk of COVID-19 cases and hospitalisations, while socio-economic deprivation of the area is a risk factor for hospitalisations. In addition, full vaccination coverage of an ABS is shown to have a protective effect on the risk of COVID-19 cases and hospitalisations in specific waves of the pandemic.
Description
Treballs finals del Màster de Fonaments de Ciència de Dades, Facultat de matemàtiques, Universitat de Barcelona. Curs: 2022-2023. Tutor: Cristian Tebé i Laura Igual Muñoz
Subject (English)
Citation
Citation
SATORRA HERBERA, Pau. Bayesian spatio-temporal analysis of the COVID-19 pandemic in Catalonia. [consulted: 6 of June of 2026]. Available at: https://hdl.handle.net/2445/214426