Tweet

https://twitter.com/franceinter/status/1339838951184609282

https://twitter.com/gro_tsen/status/1334564453816414208

More from @gro_tsen

Gro-Tsen

@gro_tsen

18 Dec

Je vais essayer de faire un petit peu de vulgarisation sur la difficulté d'interpréter causalement des statistiques de corrélation avec un exemple inventé tout simple. On cherche à savoir si les baguettes magiques étaient mieux avant. •1/19

Pour ça, on a fait des statistiques sur 100 bagues selon trois dimensions:
⁃ l'âge: la baguette est ancienne (A) ou récente (R);
⁃ la complexité: la baguette est simple (S) ou complexe (C);
⁃ si elle fonctionne bien (B) ou mal (M).
Ceci fait donc 2×2×2=8 possibilités. •2/19

Voici les statistiques qu'on a obtenues, sur un échantillon de 100 baguettes tirées au hasard:
⁃ ASM: 10
⁃ ACB: 30
⁃ ACM: 10
⁃ RSB: 10
⁃ RSM: 30
⁃ RCB: 10
(les deux autres possibilités, ASB et RCM, ne sont pas représentées). •3/19

Read 19 tweets

Gro-Tsen

@gro_tsen

17 Dec

Typography ∩ map porn: a map of Europe by dominant quotation mark styles: jakubmarian.com/map-of-quotati… (red: «x»; yellow: “x”; brown: „x“; green: „x”; blue: ”x”). I didn't realize there were so many.

I have to say, while I find all of «x», »x«, “x”, ‘x’ and „x“ (or even ‹x›, ›x‹ and ‚x‘ if anyone wants to use that), as well as "x" and 'x', equally fine, my sense of symmetry is greatly disturbed by styles such as „x” and ”x”. But it's a free world!¹

1. Restrictions apply.

At any rate, this certainly explains why Unicode characters for quotes (U+00AB LEFT-POINTING DOUBLE ANGLE QUOTATION MARK and so on) are NOT mirrored when used right-to-left, unlike parentheses.

Read 4 tweets

Gro-Tsen

@gro_tsen

16 Dec

I really wish journalists would differentiate a «lockdown», where people are forbidden from leaving their homes (or a short radius around them) or moving around freely, and closure of businesses, which in my mind isn't a «lockdown».

[Screenshot from bbc.com/news/world-eur…‌]

(I'm not enthusiastic about closure of non-essential businesses either, but at least I think they don't reach the level of drasticness as putting tens of millions of people effectively in prison for months, which is hard to justify even to save maybe tens of thousands of lives.)

Of course, it's hard to find reliable info on what various countries have done, because apparently the only aggregate data source on stay-at-home orders is ourworldindata.org/grapher/stay-a… — which is so bad in its categories that it's essentially useless.

Read 5 tweets

Gro-Tsen

@gro_tsen

11 Dec

🧵 A comparison between hydroxychloroquine and lockdowns. ⤵️

Recently I compared lockdown proponents with crackpots who believe 5G causes covid: I admit I shouldn't have written this. But the comparison with HCQ proponents, on the other hand, works very well. Thread: •1/36

Ⓐ So, first, in both cases we have something which is supposed to work against covid for a simple and not completely idiotic reason (i.e., the idea is, at least, worth considering!). •2/36

In the case of hydroxychloroquine (“HCQ” henceafter), the theory is that HCQ could serve as a zinc ionophore, transporting Zn²⁺ into the cytoplasm where it serves to inhibit viral ARN-replicase. •3/36

Read 36 tweets

Gro-Tsen

@gro_tsen

10 Dec

A claim has been brought to my attention that covid has cut life expectancy in England and Wales by a year. I think this is EXTRAORDINARILY misleading, so it deserves some clarification. •1/9 theguardian.com/world/2020/dec…

The thing is, life expectancy (at birth, or at any other age) is a bizarre notion. It is obtained by taking observed death rates by age at a given time (generally averaged over several years), assuming these rates stay constant, and computing expectancy from that. •2/9

So it's a concept which basically embeds the assumption that death rates hold constant over time. Which isn't true, of course. When they vary slowly (e.g., due to medical progress), it still makes sense. But in the face of an extraordinary even like covid? •3/9

Read 9 tweets

Gro-Tsen

@gro_tsen

8 Dec

I should probably write a preventive thread about this, because I feel I'm going to get a few comments of the kind “more than 60% in place <X> have been infected by covid, and infections are still taking place! this proves that herd immunity DOES NOT WORK! ChEcKmAtE!!!”. •1/24

So yes, I've claimed a number of times, and I still do, that the trivial estimation of the collective immunity threshold given by the formula 1 − 1/R, which gives 60% for R=2.5, is pessimistic (but that it's hard to figure out the true value). •2/24

This is essentially because the reasoning behind this formula assumes a homogeneous population (everyone is equally likely to get infected) with perfect mixing (everyone is equally likely to infect anyone) and deviations from this lower the threshold. •3/24

Read 24 tweets

Share this page!

Gro-Tsen

Try unrolling a thread yourself!

More from @gro_tsen

Gro-Tsen

Gro-Tsen

Gro-Tsen

Gro-Tsen

Gro-Tsen

Gro-Tsen

Did Thread Reader help you today?

Like this author's thread?