Here’s a first-principles normalization—take national tests, and normalize the positives to the total number of tests performed. This assumes linear returns to testing which is wrong, but it produces a curve of the shape of ACTUAL infections (without telling you the true number, just its relative shape over time) that mirrors the death curve shifted by two weeks very closely:
That’s why the third chart each week is positive test rates! And it’s the primary stay I look at. I’d do by region but would require a scraper or new data source.
Here’s a first-principles normalization—take national tests, and normalize the positives to the total number of tests performed. This assumes linear returns to testing which is wrong, but it produces a curve of the shape of ACTUAL infections (without telling you the true number, just its relative shape over time) that mirrors the death curve shifted by two weeks very closely:
https://twitter.com/econstatsnerd/status/1276629941384331264
That’s why the third chart each week is positive test rates! And it’s the primary stay I look at. I’d do by region but would require a scraper or new data source.