Abstract
Estimates of the real death toll of the COVID-19 pandemic have proven to be problematic in many countries, Italy being no exception. Mortality estimates at the local level are even more uncertain as they require stringent conditions, such as granularity and accuracy of the data at hand, which are rarely met. The “official” approach adopted by public institutions to estimate the “excess mortality” during the pandemic draws on a comparison between observed all-cause mortality data for 2020 and averages of mortality figures in the past years for the same period. In this paper, we apply the recently developed machine learning control method to build a more realistic counterfactual scenario of mortality in the absence of COVID-19. We demonstrate that supervised machine learning techniques outperform the official method by substantially improving the prediction accuracy of the local mortality in “ordinary” years, especially in small- and medium-sized municipalities. We then apply the best-performing algorithms to derive estimates of local excess mortality for the period between February and September 2020. Such estimates allow us to provide insights about the demographic evolution of the first wave of the pandemic throughout the country. To help improve diagnostic and monitoring efforts, our dataset is freely available to the research community.
Highlights
The COVID-19 pandemic is a complex and constantly evolving phenomenon that is affecting the entire world heterogeneously
Was the first country in Europe to be hit by COVID-19, and, to date, it ranks among the countries with the highest fatality toll
The official data on the death toll of COVID-19 are scarce at the local level, and, when available, they are likely to suffer from substantial underreporting (Ghislandi et al 2020)
Summary
The COVID-19 pandemic is a complex and constantly evolving phenomenon that is affecting the entire world heterogeneously. Using historical data on the number of daily certified deaths to estimate the number of daily deaths in the absence of the pandemic could vastly reduce the uncertainty associated with COVID-19 official data, especially at a disaggregated geographical level This study applies this approach to Italy. As the pandemic has affected the entire country, it is not feasible to use the most common counterfactual approach that compares treated and non-treated municipalities within the country In this unusual setting, the benchmark approach to estimate excess mortality — which we will call the “intuitive” approach — adopted by several national and international institutions, and employed in many scientific works (see Section 2), consists of comparing the actual number of cumulative all-cause deaths in 2020 with the numbers observed in the past for the same municipality..
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
