The most egregious thing is even a passing understanding of epidemics or statistical approaches to estimating effects would have shown a) better ways to analyze this and b) they didn't have the necessary data! Completely ignorant blog masquerading as a paper.
More broadly, there is the classic issue here with the ecological fallacy - we don't actually know if any of these variables substantially impacted mortality because all of the metrics are too high level
-
-
For example, most deaths in China happened in Wuhan/Hubei, but they've reportedly used the nationwide statistics for most variables. That's an issue, because Wuhan may not be representative of the whole country!
-
Oh, also I don't think the duration of mask wearing variable makes sense even if it's calculated correctly. This will skew by definition towards Asian countries that experienced their outbreaks early (and thus have longer 'durations') but will tell us nothing about masks
- Show replies
New conversation -
-
-
Mask protection is a population concept. Your mask protects me, mine protects you. In countries where 98% wear masks, they protect the other 2%. In countries where 98% don't wear masks, the mask-wearing 2% still at higher risk from others' droplets.
-
We acknowledged ecological fallacy. That affects recent Nature lockdown papers too. But we must look at whole population, not individuals, as per last tweet. Doubtful anyone will randomize entire countries to mask or not. So, this may be the best we will ever be able to do.
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.