3) First, the highlight is that mask mandates decreased COVID in schools, P<0.001.
Which, sure, it would be pretty weird if they didn't decrease COVID *at all*. But--everything's a tradeoff.
How much impact do they have?
Conversation
Replying to
Absolute % change in COVID risk seems misleading for what this study is evaluating. Masks *did* have a large impact relative to the increased COVID risk at school, cutting the increase by 50%+. The reason the absolute change was so small is the % is so small to begin with: ~0.04%
1
1
4
Replying to
Oh I totally agree it matters! But it matters as a matter of policy context, not really this study in particular. The study does suggest masks in school work and have a large effect. Whether the underlying problem is even big enough to be worth the effort is a separate question
2
Replying to
I disagree that it shows they have a large effect. It shows they have a large effect *relative to the baserate*, but the baserate is really low, so I think it's actually a small effect.
1
2
1
Replying to
If I cut the rate of a certain cancer by 50%, we would call that a large effect regardless of the fact that the base rate is tiny
1
1
The relative rate is more significant *to this specific study* because the study is looking at the effectiveness of masks, not the absolute prevalence and danger of COVID in schools
1
1
In fact by your logic if the relative effect was 100%, you would still say the effect is small
2
1
1
Replying to
agreed, in this case, that would also be small
Replying to
To me then that seems like an odd way to present this study without explaining that subtlety. I guess my point is presenting scientific results to the public, with all the appropriate context and subtlety is just plain *hard*. There isn’t always a single “correct” perspective
2
Show more replies