←back to thread

275 points rntn | 2 comments | | HN request time: 0.02s | source
Show context
dynm ◴[] No.45158964[source]
This article repeats the common mistake of conflating correlations and causality. The main results are (1) that PM2.5 exposure is correlated with dementia in humans, (2) some experimental results with mice. This does not establish causality in humans. The paper is careful to stay juuuust on the right side of the line by carefully using "associated" in the right places. But the press release discards that pretense at rigor and jumps straight to full-on claims of causality in people:

> Long-term exposure accelerates the development of Lewy body dementia and Parkinson’s disease with dementia in people who are predisposed to the conditions.

I think it's entirely possible (perhaps even likely) that this is true. But the paper does not show it.

replies(7): >>45159286 #>>45159316 #>>45160008 #>>45160027 #>>45160407 #>>45161004 #>>45161379 #
Avshalom ◴[] No.45160008[source]
Oh yeah, sure definitely it's just as likely that people predisposed to dementia move to places with high air pollution...
replies(8): >>45160024 #>>45160169 #>>45160435 #>>45160535 #>>45160632 #>>45160873 #>>45160906 #>>45161009 #
romaaeterna ◴[] No.45160435[source]
Well, in some cases we know that they do.

Dementia is linked to diabetes. And diabetes risk is increased for African-Americans. And African-Americans live in high-pollution urban areas for entirely historical reasons.

So some amount of the causation here does go in the way opposite to what a person might naively suspect.

replies(2): >>45160516 #>>45160966 #
1. JumpCrisscross ◴[] No.45160516{3}[source]
> Dementia is linked to diabetes. And diabetes risk is increased for African-Americans. And African-Americans live in high-pollution urban areas for entirely historical reasons

A is correlated with B. B is causally correlated with C, i.e. C causes B. (C is correlated with D.) Hence C causes A.

Let’s replace. Flowers are correlated with bees. Bees are caused by hives. (Hives are correlated with trees.) Hence, hives cause flowers.

Loosely, yes. Formally, no.

replies(1): >>45160742 #
2. romaaeterna ◴[] No.45160742[source]
We know that diabetes causes some amount of dementia and that flowers cause no amount of bees. And so on. Your example is specious, and obviously so.