Quote:
Originally Posted by O.city
Can one of you statistically inclined fellas explain Simpsons paradox to me
|
I don't fully understand it, but the illustrations on the right side of this page help a little bit:
https://en.wikipedia.org/wiki/Simpson%27s_paradox
Essentially, there is a causal relationship between age and severity of illness (e.g., older people are more likely to be hospitalized), and just throwing them all into one bucket makes the assumption that that relationship doesn't exist. So you end up with the efficacy numbers overall looking bad for all age groups when the reality is that you just threw a ton of people who were more likely to be seriously ill in the first place into the mix.
In short, this is an example of why random people on the internet like us should just step back and let the experts deal with it.
(And also, the vaccines work. Big surprise.)