Epidemiology of Coronavirus COVID-19: Forecasting the Future Incidence in Different Countries
This paper forecasts the future spread of COVID-19 by exploiting the identified lead-lag effects between different countries. Specifically, we first determine the past relation among nations with the aid of dynamic time warping. This procedure allows an elastic adjustment of the time axis to find si...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-04-01
|
Series: | Healthcare |
Subjects: | |
Online Access: | https://www.mdpi.com/2227-9032/8/2/99 |
id |
doaj-f936e08131cf4c0894a39473c78f0aa8 |
---|---|
record_format |
Article |
spelling |
doaj-f936e08131cf4c0894a39473c78f0aa82020-11-25T03:24:03ZengMDPI AGHealthcare2227-90322020-04-018999910.3390/healthcare8020099Epidemiology of Coronavirus COVID-19: Forecasting the Future Incidence in Different CountriesJohannes Stübinger0Lucas Schneider1Department of Statistics and Econometrics, University of Erlangen-Nürnberg, Lange Gasse 20, 90403 Nürnberg, GermanyDepartment of Statistics and Econometrics, University of Erlangen-Nürnberg, Lange Gasse 20, 90403 Nürnberg, GermanyThis paper forecasts the future spread of COVID-19 by exploiting the identified lead-lag effects between different countries. Specifically, we first determine the past relation among nations with the aid of dynamic time warping. This procedure allows an elastic adjustment of the time axis to find similar but phase-shifted sequences. Afterwards, the established framework utilizes information about the leading country to predict the Coronavirus spread of the following nation. The presented methodology is applied to confirmed Coronavirus cases from 1 January 2020 to 28 March 2020. Our results show that China leads all other countries in the range of 29 days for South Korea and 44 days for the United States. Finally, we predict a future collapse of the healthcare systems of the United Kingdom and Switzerland in case of our explosion scenario.https://www.mdpi.com/2227-9032/8/2/99CoronavirusCOVID-19epidemiologyincidencedynamic time warpinglead-lag effects |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Johannes Stübinger Lucas Schneider |
spellingShingle |
Johannes Stübinger Lucas Schneider Epidemiology of Coronavirus COVID-19: Forecasting the Future Incidence in Different Countries Healthcare Coronavirus COVID-19 epidemiology incidence dynamic time warping lead-lag effects |
author_facet |
Johannes Stübinger Lucas Schneider |
author_sort |
Johannes Stübinger |
title |
Epidemiology of Coronavirus COVID-19: Forecasting the Future Incidence in Different Countries |
title_short |
Epidemiology of Coronavirus COVID-19: Forecasting the Future Incidence in Different Countries |
title_full |
Epidemiology of Coronavirus COVID-19: Forecasting the Future Incidence in Different Countries |
title_fullStr |
Epidemiology of Coronavirus COVID-19: Forecasting the Future Incidence in Different Countries |
title_full_unstemmed |
Epidemiology of Coronavirus COVID-19: Forecasting the Future Incidence in Different Countries |
title_sort |
epidemiology of coronavirus covid-19: forecasting the future incidence in different countries |
publisher |
MDPI AG |
series |
Healthcare |
issn |
2227-9032 |
publishDate |
2020-04-01 |
description |
This paper forecasts the future spread of COVID-19 by exploiting the identified lead-lag effects between different countries. Specifically, we first determine the past relation among nations with the aid of dynamic time warping. This procedure allows an elastic adjustment of the time axis to find similar but phase-shifted sequences. Afterwards, the established framework utilizes information about the leading country to predict the Coronavirus spread of the following nation. The presented methodology is applied to confirmed Coronavirus cases from 1 January 2020 to 28 March 2020. Our results show that China leads all other countries in the range of 29 days for South Korea and 44 days for the United States. Finally, we predict a future collapse of the healthcare systems of the United Kingdom and Switzerland in case of our explosion scenario. |
topic |
Coronavirus COVID-19 epidemiology incidence dynamic time warping lead-lag effects |
url |
https://www.mdpi.com/2227-9032/8/2/99 |
work_keys_str_mv |
AT johannesstubinger epidemiologyofcoronaviruscovid19forecastingthefutureincidenceindifferentcountries AT lucasschneider epidemiologyofcoronaviruscovid19forecastingthefutureincidenceindifferentcountries |
_version_ |
1724603647787008000 |