We look at the COVID-19 confirmed cases for US counties compared to various demographics, vaccinations and Presidential election results.
Vaccinations
Vaccination data per county are from: https://data.cdc.gov/Vaccinations/COVID-19-Vaccinations-in-the-United-States-County/8xkx-amqh/data
Confirmed cases per county data are from: https://usafacts.org/visualizations/coronavirus-covid-19-spread-map/. Note that Hawaii, Texas and Alaska data is missing.
Presidential election results are from: https://raw.githubusercontent.com/tonmcg/US_County_Level_Election_Results_08-20/master/2020_US_County_Level_Presidential_Results.csv
Fig 1 | Fig 2 |
|---|---|
|
|
In Fig 1 it is seen that counties that voted for Biden have a higher vaccination rate. The average full vaccinations for Beiden are 44% +- 16% versus 36% +- 13% for Trump.
The trendline in Fig 2 shows a negative slope indicating the more the county leans to Trump the less likely people are to be vaccinated.
Looking in more detail at the Trump and Biden election return distributions we see below:
| Fig 3 | Fig 4 from | Fig 5 |
|---|---|---|
|  |
|
It is seen in Fig 3 that there are over four times more counties won by Trump compared to counties won by Biden. This can also be observed in Fig 4 by looking at a map of results by county from https://brilliantmaps.com/2020-county-election-map/. However, as one includes the county populations in Fig 5 by means of a bubble plot one can see the impact leans more to Biden.
Various Demographics
Here we look at the correlations between various demographics etc.
Presidential election 2020
Another way of observing how Biden was more popular in the more densely populated counties is seen in Fig 6 where we plot the point difference against the population density and see that the Pearson R2 correlation (a measure of the total variation of y explained by the predictor (regressor) x) is ~28%, and the Pearson r (the correlation between x and y) = sqrt(R2) ~ 53%.
| Fig 6 |
|---|
|
