Functional cluster and canonical correlation analysis of EU countries by number of daily deaths and stringency index during Covid-19 pandemic


Keser İ., Deveci Kocakoç İ.

ELECTRONIC JOURNAL OF APPLIED STATISTICAL ANALYSIS, vol.14, no.1, pp.197-216, 2021 (ESCI) identifier identifier

  • Publication Type: Article / Article
  • Volume: 14 Issue: 1
  • Publication Date: 2021
  • Doi Number: 10.1285/i20705948v14n1p197
  • Journal Name: ELECTRONIC JOURNAL OF APPLIED STATISTICAL ANALYSIS
  • Journal Indexes: Emerging Sources Citation Index (ESCI), Scopus, Academic Search Premier, zbMATH
  • Page Numbers: pp.197-216
  • Keywords: Covid 19, pandemic, functional cluster analysis, functional canonical correlation analysis, public health
  • Dokuz Eylül University Affiliated: Yes

Abstract

The danger of a global pandemic, such as the new Coronavirus (Covid-19), is obvious. This study aims to investigate the behavior and relationship of the number of daily new confirmed deaths per million and the stringency index of twenty-seven European Union (EU) countries by utilizing functional cluster analysis and functional canonical correlation analysis. Functional cluster analysis was used to observe how countries cluster together according to daily deaths during the time interval between March and July 2020. Functional canonical correlation analysis was also utilized to measure the correlation between the frequency index and daily deaths, and also to determine the relative positions of countries concerning their respective variability structure. The data is obtained from OWID. Here, it is seen that Italy, Spain, Belgium, and France are particularly affected by the pandemic during the time interval within the EU countries, and the course of daily deaths is in a different position compared to other EU countries. At the same time, a very high relationship emerged between the stringency index and daily deaths as expected.