This isn't that, and I've talked (at length, repeatedly) about why the smoking example is interesting and a special case. I am not going retread old ground here. Same with RCTs not being the only acceptable form of causal inference. That doesn't excuse this, at all.
-
-
Do people who comply with one non-pharmaceutical intervention comply with others? Probably. (That’s also why that whole risk compensation thing was mostly nonsense.) Do they all add up? Almost certainly. Relative contribution is hard to measure (non-linear) but we can estimate.
-
My whole thing is examining how well we can actually estimate these things in any meaningful sense. In COVID in particular, everything gets much, much harder to the point of near-hopelessness for many questions. I think we all need to get much more comfortable with that.
- Show replies
New conversation -
-
-
Be interesting to see if mask use is anti correlated with age adjusted disease severity https://www.nejm.org/doi/full/10.1056/NEJMp2026913 …
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Relevant to your point:https://twitter.com/analisereal/status/1317276482641612802 …
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
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.