Undersampling in action and at scale: application to the COVID-19 pandemic

Andreas Langousis; Alin Andrei Carsteanu

doi:10.1007/s00477-020-01821-0

Undersampling in action and at scale: application to the COVID-19 pandemic

Stoch Environ Res Risk Assess. 2020;34(8):1281-1283. doi: 10.1007/s00477-020-01821-0. Epub 2020 Jun 2.

Authors

Andreas Langousis¹, Alin Andrei Carsteanu²

Affiliations

¹ Department of Civil Engineering, University of Patras, Patras, Greece.
² ESFM, Instituto Politécnico Nacional, Ciudad de México, México.

Abstract

It is the purpose of this short communication to analyze the possible caveats in the statistical interpretation of collected data, particularly in the light of decision-making concerning the current COVID-19 coronavirus pandemic. A mitigation of undersampling is proposed, based on re-scaling of statistics that can be considered reliable, such as deaths, and epidemic properties like mortality, that may be considered comparable between countries with similar levels of health care, which would not have reached a saturation level.

Keywords: Asymptomatic carriers; COVID-19 pandemic; Susceptible-infectious-removed (SIR) models; Undersampling.