A single graph explains the effect of vaccines on mortality. The rest is statistical trickery.

[Unless past infected off by >1 order of magnitude.]

"Dan from Prague" @maircomm arguing w/Jordan Peterson who has the scientific rigor of a drunk astrologist.
2) This does not count the infections that were *avoided* by vaccines (conservatively estimated > 50%).

PS- I blocked Peterson 2 y ago when he invited me to do a podcast & didn't know much abt him. Went to his feed, listened to a podcast, was horrified, and blocked.
Fine print: (Clearly there is a possibility that the virus became suddenly 10x less deadly or that the old miraculously ceased to be infected in favor of the young or that the agencies are paid by Pharma to lie and other ad hoc arguments)
Fine print: (Clearly there is a possibility that the virus became suddenly 10x less deadly or that the old miraculously ceased to be infected in favor of the young or that the agencies are paid by Pharma to lie and other ad hoc arguments)
3) This is a (nearly) contemporaneous U.S. data [mostly Delta variant]. Unless there is a mysterious Specter-like group [007] manipulating the data or some vast conspiracy, vaccines substantially reduce the rate of infection.
There are >> infections, consider the counterfactual.
4) Compare the UK [1 in thread] to Russia [less vaccinated]. Pace some adhocnitpicker that one needs to control for Vodka & readership of Dostoevski.

• • •

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

Keep Current with Nassim Nicholas Taleb

Nassim Nicholas Taleb 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 @nntaleb

9 Nov
"You'd rather impress your cardiologist than gym rats"

You need to be BOTH strong AND aerobically fit -it's not not either/or.

There are no RCS for both exercises jointly [only separately] but we know that strength training stiffens LV, aerobic reserse-remodels.

@DrDamluji
2) We humans are not made to specialize without costs. Doing "too much" aerobic is worse than the optimal level ["reasonably" fit but without too much hypertrophy], but still better than sedentary.
Being strong is a necessity. But there must be a similar optimum.
3) Rigorous longitudinal RCS: as we age, we need >> than the recommended 150 min/w. Add 90% MHR 1 day plus strength training 1 day, but much less than prof athletes.

Entire bandwidth: Utraslow walks + brisk + stairs/hikes/sprints as no 1 is a substitute.
Read 7 tweets
30 Oct
Friends, *Hyperinflation* seems to exist in the minds of noise-prone pple on Social Media than in the numbers.

1) COMMODITIES: The CRB is lower than it was in 2014 and waaaaay lower (50%) than 2007.

2) SHIPPING: The Baltic Dry Index is 60% *below* 2007.

Jst local disruptions.
2) So what we have to worry about is the asset price inflation resulting from low rates; these historically have collapsed at the first sign of tightening.

Vulnerable (by order): Cryptos, Residential Upper End Real Estate, Stocks, Residential RE, etc.
3) Lumber has been most sensitive because of real estate but it gave back almost ALL gains, at 2018 levels.

Read 4 tweets
16 Oct
Friends and CardioTwitter,
How can Heart Rate Variability (#HRV ) be informative if it moves intraday by 1 order of magnitude?
Another statistical problem: standard deviation must not be stochastic for standard metrics.
Is it so observation dependent?
Looks like HRV may contain *some* information in very long term trends but this shows you observe mostly noise.
No single observation has observation unless it is in the very far tail.
OK, OK
HRV data fits the Lognormal like a glove. A high variance Lornormal (Max=40 times Min!), so not good news. I would ignore the metric even if it seems to selectively fit some diagnosis of Covid or overtraining.
Read 4 tweets
12 Sep
Before we delve into the statistics in the paper, please note an R^2 of .03. It means more than 99% can be explained by randomness.
Please note that I have a technical blog, largely focused on uses and misuses of probability in #Medicine. But one can get some entertainments from psycholophasters.

fooledbyrandomnessdotcom.wordpress.com/2021/09/07/est…
Basically, Mr Grant, can you explain to us who you are bullshitting ?
Where is the class of people who buy this crap?

@AdamMGrant
cc:@marissa_sharif @cmogilner @HalHershfield
Read 5 tweets
27 Aug
I am all for freedom.
But then hospital staff MUST also have the freedom to treat you last, give priority of resources to people who promote safety for themselves and others, no?
Freedom!
[Texas Anti-Mask 'Freedom Rally' Organizer Fighting For His Life With COVID-19]
2) Freedom must come with consequences and reciprocity.
[Being smoker/obese or having a risk factor is not in your control and is not MULTIPLICATIVE. Asking for freedom to SPREAD Covid is something different.]
3) For idiots not getting it, an obese person is only harming herself or himself. Someone who wants to spread Covid is actively harming others, and so in a multiplicative way.

Libertarianism is FIRST about non-aggression.

#Scaling
Read 5 tweets
22 Aug
PROBABILITY DU JOUR
You can see with the naked eye that the data in the Ariely paper was fabricated: for annual miles driven, STDEV ~ ½ mean. For a one-tailed distribution, this MUST be Uniform, flat frequ. in [a,b].
Miles per annum CANNOT be uniform SINCE they are a sum: CLT! Image
2) Here is the story (softly) retracted from PNAS. Someone cheated in the food chain, and there was no need for the graphs below to figure it out.

economist.com/graphic-detail… Image
3) The Ariely paper (cont):
This very very short video explains why ~ NO sum can be uniform.

Read 6 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

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us on Twitter!

:(