A Statistical Comparison of COVID-19 in the United States Across Political Affiliations and Census Regions

In mid-January 2020, the United States reported their first cases of the coronavirus disease (COVID-19) from a passenger returning from Wuhan, China. Initially, the situation wasn’t very alarming as in China and European countries, but the situation began to worsen in March 2020 when the number of cases began to multiply. Then, in a matter of a few months, the United States became the number one country in terms of total cases and total deaths from COVID-19. We have been closely observing the United States and the world since July 2020. Our study aims to compare the political affiliations and census regions of the United States in terms of severity of the COVID-19 pandemic. During our study period, the United States experienced several waves and the start of the vaccination distribution. We expect that our study is able to capture the effects of these events. We consider the following variables associated with COVID 19 – Case Fatality Rate, Total Cases over Population, Total Deaths over Population, COVID-Like Symptoms in the Community, People Wearing Masks, and Vaccine Acceptance in the United States. For studying the first three variables, we consider 140 randomly chosen days from April 2020 through May 2021 and generate our data on these variables using the Worldometers website. We perform appropriate statistical tests to do comparisons (1) across political affiliations (the 2020 Presidential Election and the Gubernatorial Elections as of 2020), and (2) across census regions. Secondly, for each of the political affiliations and for each region, we split the data into two halves and compare the first 70 days versus the last 70 days for our variables. For the remaining three variables, COVID-Like Symptoms in the Community, People Wearing Masks, and Vaccine Acceptance, we generate our data using the COVID Cast website. We consider 80 random days from January 2021 through August 2021 for studying COVID-Like Symptoms in the Community (per 100 people), 67 random days from February 2021 through August 2021 for studying People Wearing Masks (percentage out of 100), and 33 random days from May 2021 through August 2021 for Vaccine Acceptance (per 100 people) in the United States. We perform similar political affiliation-wise and region-wise comparisons for these three variables. For our political affiliation-wise and region-wise comparisons, we use Welch two sample t-test, Wilcoxon rank sum test, Spearman’s rank correlation, and Kendall’s tau-b correlation coefficient for all our variables. For three of the variables, namely, Case Fatality Rate, Total Cases over Population, and Total Deaths over Population, we split our data into first 70 days versus the last 70 days and compare for each political affiliation and census region using Spearman’s rank correlation, and Kendall’s tau-b correlation coefficient. Further, for Case Fatality Rate, we also perform paired t-tests and Wilcoxon signed rank tests. For four of the variables, namely, Case Fatality Rate, COVID-Like Symptoms in the Community, People Wearing Masks, and Vaccine Acceptance, we do political affiliation-specific and region-specific trend analysis through the Mann-Kendall trend test. The study has a number of limitations though. For example, in the future, we will rather apply multiple comparison techniques such as ANOVA or Kruskal Wallis for comparing across regions.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.