1/ with thanks to @JustTheFacts37 for sharing data, I am now loaded for bear and ready to take on @JasonSalemi !

the good and (too) fair Dr, Jason has claimed %Pos for New Cases to be a useful and worthwhile metric. I have disagreed (with words). Now, I can provide the data.👇
2/these data show the number of "total tests" as collated from the daily .pdf by @JustTheFacts37. From that I have deducted the total of "new people tested", leaving the total of tests of people who are not "new," aka "retests"
It's clear that most of all tests are now retests.👇
3/ The impact of including this mass of retests into a %Pos value is also clear. As the % of tests that are retests increases, the "%Pos for New Cases" decreases.
Why? b.c the population of retested people tests (+) less often, thus lowering the overall %Pos.
👇
Thus
"All '%Pos for New Cases' really measures is the proportion of 'retests' to 'new tests' "

Not very useful & NOT AT ALL what the WHO & CDC were talking about when setting benchmarks of 10% & 5%.

I have nothing but respect for @JasonSalemi and all he has done and is doing👇
...and will continue to do for Floridians.
If there was ever an example of someone being "too fair," Dr. Jason is it.

But "too nice of a guy" is hardly an insult.
Carry on!

(This thread is an homage to an old debate, it just takes this old sailor some time to come about!)

• • •

Missing some Tweet in this thread? You can try to force a refresh
 

Keep Current with Christopher R. Perle, PhD (Biologist, since birth)

Christopher R. Perle, PhD (Biologist, since birth) Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @DrSeaPerle

14 Oct
#DeathRace2020 #WeeklyUpdate shows the peak still growing @HealthyFla (a lot) 10 weeks later. Recent deaths make up the rest of the 680-730 (wonky) reported deaths for the week. Late August not as much.
No "net weekly deletions" unlike last week.
How long will the lags continue? Image
#DeathRace2020 added 735 deaths in the #weeklyupdate, but that included Sunday, so we deleted 50 (one per day for 50 days). Either way, reported deaths @HealthyFla are not declining, but due to lags, maybe recent deaths are?
Maybe, hard to say when >50% of deaths are 6+ weeks old Image
#DeathRace2020 #weeklyupdate knows there is a backlog @healthfyfla in late July/early Aug, but weeks 10 and 11 weeks ago were 22% of all reported deaths last week. This past week was only 10% of all deaths reported.
Were there fewer recent deaths to report? Or do they also lag? Image
Read 4 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Too expensive? Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal Become our Patreon

Thank you for your support!

Follow Us on Twitter!