Through the recent months, the number of COVID-19 cases all over the world has continued to grow. By examining recent COVID-19 statistics present in the owid-covid-data.csv, our group tried to figure out which factors that the world could focus on that would have an impact on the curve of COVID-19
First off, our group calculated the correlation coefficients between the most recent Total Cases Per Million (TCPM) and other factors seen in the csv file.
We then picked which of the correlations could have meaning in our study. For example, we didn't bother looking at the correlation between the most recent TCPM and New Cases Per Million since there is not much to learn from determining how correlated these two are.
The factors that we found to have meaning in our study were the following, along with their respective correlation coefficients:
Most recent Total Cases Per Million (TCPM) vs constant factors
Our group believed that we would get more accurate correlation results if we compare the most recent TCPM instead of New Cases (NC) to other constant factors since the most recent TCPM can indicate how well a location is presently dealing with the pandemic. If we used NC instead for comparisons with a constant factor, we would need to look at the trend of NC and judge by sight how correlated the trend is to each constant factor, which would be a tedious process.
We only used the factor NC whenever we're comparing it with a dynamic factor (changes over time). In our study, we compared NC with Stringency Index (SI) by looking at the trends of a few chosen locations. These comparisons will be further elaborated in section IV.
As a rule of thumb, here is how we interpret these correlation coefficients ($r^2$):