A look at the spatio-temporal mortality patterns in Italy during the COVID-19 pandemic through the lens of mortality densities

Abstract

With the tools and perspective of Object Oriented Spatial Statistics, we analyze official daily data on mortality from all causes in the provinces and municipalities of Italy for the year 2020, the first of the COVID-19 pandemic. By comparison with mortality data from 2011 to 2019, we assess the local impact of the pandemic as perturbation factor of the natural spatio-temporal death process. For each Italian province and year, mortality data are represented by the densities of time of death during the calendar year. Densities are regarded as functional data belonging to the Bayes space In this space, we use functional-on-functional linear models to predict the expected mortality in 2020, based on mortality in previous years, and we compare predictions with actual observations, to assess the impact of the pandemic. Through spatial downscaling of the provincial data down to the municipality level, we identify spatial clusters characterized by mortality densities anomalous with respect to the surroundings. The proposed analysis pipeline could be extended to indexes different from death counts, measured at a granular spatio-temporal scale, and used as proxies for quantifying the local disruption generated by the pandemic.

Research Trends on Functional Data Analysis Using Scopus Database: A Bibliometric Analysis

“…Since [70], used functional data analysis to conceptualise and explore the comparative efficacy of various nonpharmaceutical interventions that countries could use to prevent or slow the spread of disease incidence and death. In addition, Scimone et al [71] examined the spatio-temporal mortality patterns of COVID-19 cases in Italy. In their analysis, the mortality data were represented as densities of time of death, considered functional data.…”

Application of Data Science for Cluster Analysis of COVID-19 Mortality According to Sociodemographic Factors at Municipal Level in Mexico

“…Given the availability of public epidemiological data on COVID-19 in many countries, several studies have focused on the analysis of patterns of similarity in incidence and mortality rates of COVID-19 and clustering by geographical areas [2,3]. Some of the approaches of these studies have been the analysis of temporal trends of mortality rates [4][5][6][7] as well as the identification of geospatial patterns and critical points of mortality rates and their relationship with socioeconomic, political and environmental variables [8][9][10][11]. A recent study evaluated the spatial pattern of the COVID-19 mortality rate as well as hotspots and health and socioeconomic predictor variables in contiguous United States counties, finding that hotspots for COVID-19 mortality 19, as well as socioeconomic variables, are primarily delineated in the south, Midwest, and northeast of the contiguous United States.…”

Generalised functional additive mixed models with compositional covariates for areal Covid-19 incidence curves

“…Although this approach provides a promising framework for density-valued response regression, extensions which (additionally) allow for densityvalued explanatory variables remain extremely limited. A first linear Bayes Hilbert space regression model for scalar responses and density-valued covariates was proposed by Talská et al (2021) using a constrained spline representation (Machalová et al, 2021) and extended further by Scimone et al (2021), allowing for both density-valued responses and covariates. While this model allows for linear effects of the functional composition on the response, extensions to generalised (functional) additive models where parts of the predictor are finite or infinite compositions still remains an open topic.…”