> What they did was simple: they looked at the fraction of patients who tested positive for #COVID19 at the clinics they own. They found 340 out of 5213 tests were postive, about 6.6%
> Then they assume the same fraction of the whole population are infected.
6.6% infected has to be wrong. That just shows we're not testing enough to see the true, much lower, number. It's also biased because we're not randomly sampling--instead we're testing people that are already showing symptoms.
Then when that inflated number goes in the denominator, it makes it look like the fatality rate is much lower.
Are you really prepared to say a claim of 6.6% is so misleading it needs to be removed?
* http://publichealth.lacounty.gov/phcommon/public/media/media...
The sensitivity is the issue, but that would tend to push the true infected % up not down.
https://www.medrxiv.org/content/10.1101/2020.04.15.20066407v...
Not surprising, though.
Idiotic (and, yes, such an error IS idiotic) fumbling with statistics is displayed on a daily basis.
It doesn't matter what 'side' you are on: idiots abound.
Doomer fallacies: Charts showing exponential growth of positives, without taking into account the exponential growth of tests...
Flu-Bro fallacies: Antibody surveys that don't take into account false positives and make no mention of the expected number of positives in a population (both needed to make ANY sense of the results.)
Doomer fallacies: No distinction between dying 'with' versus dying 'from'.
Flu-Bro fallacies: Relying on death counts from the Chinese Communist Party.
Doomer fallacies: Comparing 'positive' test rates between populations and countries with utterly different criteria for administering tests.
etc.
One thing you can count on, though: You will usually get a downvote on Hacker News if you deviate from the mainstream.
Previously you were in a discussion with me arguing with great confidence that the virus outbreak would be a distant memory in two months. I just looked it up; it was 61 days ago.
https://news.ycombinator.com/item?id=22434499
You were using terms like "chicken littles" then. I'm all for reading different viewpoints, but if you're going to throw around insults like "doomer", you're not likely to get a civilised discussion going.
So, so I was a few days off in my estimate.
Statistically insignificant deaths, no overwhelmed hospitals, no body bags in the hallways or rationing of ventilators. No millions of deaths now any other of the nonsense being predicted here two months ago.
The talk now, as evidenced by the front page, is other topics... stimulus checks and the like.
Are things as you feared two months ago?