COVID-19 Data Dispatch

Tag: how to understand data

  • How to understand COVID-19 numbers

    OG readers may remember that, in my first issue, I praised a ProPublica article by Caroline Chen and Ash Ngu which explains how to navigate and interpret COVID-19 data. I was inspired by that article to write a similar piece for Stacker: “How to understand COVID-19 case counts, positivity rates, and other numbers.”

    I drew on my experience managing Stacker’s COVID-19 coverage and volunteering for the COVID Tracking Project to explain common COVID-19 metrics, principles, and data sources. The story starts off pretty simple (differentiating between confirmed and probable COVID-19 cases), then delves into the complexities of reporting on testing, outcomes, and more. As a reader of this newsletter, you likely already know much of the information in the story, but it may be a good article to forward to friends and family members who don’t follow COVID-19 data quite so closely.

    (I also made a custom graphic for the “seven-day average cases” slide, which was a fun test of my burgeoning Tableau skills.)

  • Which COVID numbers you should pay attention to, actually

    My last big story for this week is to heavily recommend this ProPublica feature by Caroline Chen and Ash Ngu on how to navigate COVID-19 data. Chen is a veteran health journalist who has been reporting on COVID-19 since January (and who reported on previous disease outbreaks before that). Her story explains how to understand test positivity rates, data lags, and the inherent uncertainty that comes with any attempt to quantify this pandemic.

    You should really read the full story, but I’ll summarize the main points for you here in case you’re just going to bookmark it for later:

    • Test positivity rates indicate the share of COVID-19 tests in a region which are coming back positive. If the rate is high (above 10%), this may mean only sick people have access to tests, and testing is not occurring widely enough to fully capture the scale of an outbreak. If the rate is low (below 5%), this may mean anyone who wants a test can get one, and epidemiologists will be able to quickly identify and trace new outbreaks.
    • Daily case counts often are not a good indicator of how a region’s outbreak is progressing, because counts of new cases may be undercounted on weekends or during testing delays. For a more accurate picture, look at the seven-day rolling average—a figure that averages a particular day’s number of new cases with the numbers of the six previous days. Also, rises in deaths tend to lag rises in cases by several weeks, reflecting the progression of the disease in COVID-19 patients.
    • It is difficult to state definitively whether a certain event—such as a restaurant opening or a protest—impacted COVID-19 spread in an area. No one event occurs in a vacuum, and any resulting data around that event were likely impacted by testing lags, testing availability, and other factors.
    • Don’t just look at one statistic; look at the whole picture. Ask whether case counts are rising in your area, yes, but also ask: are enough people getting tested? Are the hospitals filling up? How does your state or county compare to others nearby?
    • Find and follow sources you trust to help you interpret data as they are released. A good source will advise you in the areas where they have expertise and let you know when a question is out of their wheelhouse.