Re:Coronavirus: Santa Clara County has had 50 to 85x more ca...
by Gibbon1 on Friday April 17, 2020 @09:00PM
(#22904444)
My summary is when betting on any test with a low positive rate take under not the over.
Saying at least this many people have been infected, wrong. Better. At most this many people have been infected.
Reminds me of a survey 15 years ago that said something like 2-3% of black people approved of the job the president was doing. That 2-3% was more likely 'rectified noise'.
Re:Coronavirus: Santa Clara County has had 50 to 85x more ca...
by SpicyLemonZest on Saturday April 18, 2020 @12:39AM
(#22905360)
In normal times, where there aren't critically urgent decisions to be made, that's the right approach. We don't have that luxury right now; we're continually charting the path forward, and if we don't have clean data then we'll need to chart it with unclean data.
And I think it's hard to argue that this study is worse than our existing case data, which is simply a daily aggregate of the number of new positive PCR tests labs report they've run. That's not even attempting to be a statistically valid estimate.
Re:Coronavirus: Santa Clara County has had 50 to 85x more ca...
by viztor on Saturday April 18, 2020 @05:15AM
(#22906373)
for 3, sampling bias would not account for much as the coronavirus will catch you regardless of someone's socio-economical status. The difference is mostly just survival rate.
https://medium.com/@balajis/peer-review-of-covid-19-antibody...
A summary of his post:
1. There were 2 false positives in 401 pre-covid samples (known negative). Assuming a normal distribution, 2 sigma confidence can account for up to 80% of the positive results reported in this study.
2. For the virus to have already infected this many people, it should’ve spread so fast that it doesn’t match what we know about similar epidemics.
3. The researchers recruited volunteers via facebook ads. There could be sampling bias here.
I encourage everyone to read the article: my summary < The original article.