There’s still no sign of a winter wave in the U.S., plus or minus some data reporting issues.
Near as I can tell, the U.S. remains at about 12 new COVID-19 cases per 100K population per day.
I’ll try to explain the data glitch.
States have been skipping days of data reporting for some time now. That got frequent enough that I re-wrote the program I use to process the data to gap-fill those missing values. It wasn’t perfect, but it keep the reporting-driven variation in the graphs to a minimum.
We have now reached point where some states routinely skip new case reporting for weeks at a time. My little gap-fill method can’t handle that, because a) you can no longer calculate a seven-day moving average, and b) you have to do some fancy footwork to get anything like a sensible average. E.g., if today’s number for South Carolina is the first new data reported in two weeks, I need to divide that by 14 to estimate new cases per day.
The upshot is that to handle this new wrinkle in some states’ data reporting, the simple notion of add-the-last-seven-then-divide-by-seven has to be replaced with a chunk of logic, conditional on how many days the state skipped.
I really don’t feel like rewriting the core of my data processing code just to handle that. Not unless a lot of states are getting into the habit of reporting every other week or even less frequently.
So, for the time being, I’m just noting that the apparent uptick is driven this mismatch between data reporting and data processing. And leaving it at that.
Data source for this and other graphs of new case counts: Calculated from The New York Times. (2021). Coronavirus (Covid-19) Data in the United States. Retrieved 10/29/2022, from https://github.com/nytimes/covid-19-data.” The NY Times U.S. tracking page may be found at https://www.nytimes.com/interactive/2020/us/coronavirus-us-cases.html
