Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021;34(4):1189-1217.
doi: 10.1007/s00148-021-00857-y. Epub 2021 Jun 19.

Local mortality estimates during the COVID-19 pandemic in Italy

Augusto Cerqua  1 , Roberta Di Stefano  2 , Marco Letta  1 , Sara Miccoli  3
Affiliations

Local mortality estimates during the COVID-19 pandemic in Italy

Augusto Cerqua et al. J Popul Econ. 2021.

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.

Supplementary information: The online version contains supplementary material available at 10.1007/s00148-021-00857-y.

Keywords: COVID-19; Coronavirus; Counterfactual building; Italy; Local mortality; Machine learning.

PubMed Disclaimer

Conflict of interest statement

Conflict of interestThe authors declare no competing interests.

Figures

Fig. 1
Fig. 1
Percentage of municipal excess deaths detected from February 21, 2020, to September 30, 2020, with respect to the counterfactual scenario estimated via ML techniques. A From February 21, 2020, to March 31, 2020 (note: excess mortality estimates for the north of Italy, 23,603; official number of COVID-19 deaths, 11,011. Gap between these estimates on March 31, 12,592). B From February 21, 2020, to June 30, 2020 (note: excess mortality estimates for the north of Italy, 40,001; official number of COVID-19 deaths, 29,752. Gap between these estimates on June 30, 10,249). C From February 21, 2020, to September 30, 2020 (note: excess mortality estimates for the north of Italy, 39,362; official number of COVID-19 deaths, 30,580. Gap between these estimates on September 30, 8,782)
Fig. 1
Fig. 1
Percentage of municipal excess deaths detected from February 21, 2020, to September 30, 2020, with respect to the counterfactual scenario estimated via ML techniques. A From February 21, 2020, to March 31, 2020 (note: excess mortality estimates for the north of Italy, 23,603; official number of COVID-19 deaths, 11,011. Gap between these estimates on March 31, 12,592). B From February 21, 2020, to June 30, 2020 (note: excess mortality estimates for the north of Italy, 40,001; official number of COVID-19 deaths, 29,752. Gap between these estimates on June 30, 10,249). C From February 21, 2020, to September 30, 2020 (note: excess mortality estimates for the north of Italy, 39,362; official number of COVID-19 deaths, 30,580. Gap between these estimates on September 30, 8,782)
Fig. 1
Fig. 1
Percentage of municipal excess deaths detected from February 21, 2020, to September 30, 2020, with respect to the counterfactual scenario estimated via ML techniques. A From February 21, 2020, to March 31, 2020 (note: excess mortality estimates for the north of Italy, 23,603; official number of COVID-19 deaths, 11,011. Gap between these estimates on March 31, 12,592). B From February 21, 2020, to June 30, 2020 (note: excess mortality estimates for the north of Italy, 40,001; official number of COVID-19 deaths, 29,752. Gap between these estimates on June 30, 10,249). C From February 21, 2020, to September 30, 2020 (note: excess mortality estimates for the north of Italy, 39,362; official number of COVID-19 deaths, 30,580. Gap between these estimates on September 30, 8,782)
Fig. 2
Fig. 2
Percentage of municipal excess deaths detected from February 21, 2019, to June 30, 2019, with respect to predicted deaths estimated via ML techniques. Note: Excess mortality estimates (measurement error) at the country level: 1,365
See this image and copyright information in PMC

References

    1. Abadie A, Cattaneo MD. Econometric methods for program evaluation. Ann Rev Econ. 2018;10:465–503. doi: 10.1146/annurev-economics-080217-053402. - DOI
    1. Abrell J, Kosch M, Rausch S (2019) How effective was the UK carbon tax? A machine learning approach to policy evaluation. A Machine Learning Approach to Policy Evaluation (April 15, 2019). CER-ETH–Center of Economic Research at ETH Zurich Working Paper, 19, 317
    1. Andini M, Ciani E, de Blasio G, D'Ignazio A, Salvestrini V. Targeting with machine learning: an application to a tax rebate program in Italy. J Econ Behav Organ. 2018;156:86–102. doi: 10.1016/j.jebo.2018.09.010. - DOI
    1. Ansart S, Pelat C, Boelle PY, Carrat F, Flahault A, Valleron AJ. Mortality burden of the 1918–1919 influenza pandemic in Europe. Influenza Other Respir Viruses. 2009;3(3):99–106. doi: 10.1111/j.1750-2659.2009.00080.x. - DOI - PMC - PubMed
    1. Ascani A, Faggian A, Montresor S (2020) The geography of COVID-19 and the structure of local economies: the case of Italy. J Reg Sci, first published online: 20 November 2020 - PMC - PubMed

LinkOut - more resources