Re:The Fallacy of Placing Confidence in Confidence Intervals
by Tloewald on Sunday September 13, 2015 @06:43PM
(#10213033)
The experiment has already taken place and its findings are either correct or incorrect. It's not a Schrodinger's Cat, the Cat is alive or dead.
Imagine two studies have been completed and they have non-overlapping confidence intervals each of 95%. Does each have a 95% chance of having captured the result? Obviously not -- at most one may be correct.
I'm still not clear on this, what does it mean? I also tried to read the linked text but it's quite dense and drawn out.