[westcort]

Not mentioned here is the lady’s name, Muriel Bristol.

I have also heard that this is a different way with 6 cups. This matters because 6C3 = 6! / (3!(6-3)!) = 20. That 1/20 chance of getting all 3 cups right is said to be the basis for the 5% significance cutoff for p values.

Another basis for the 5% cutoff is the (even earlier) Poisson distribution, with zero expected events, 3 observed. In this case, the probability of occurrence by chance is 1/e^3, which is just under 5%. In other words, the 5% p value is analogous to “3 strikes you’re out” because the probability of 3 uncommon events or exceptions is <5%.

https://en.m.wikipedia.org/wiki/Muriel_Bristol

[stavros]

> The woman in question, phycologist Muriel Bristol, claimed to be able to tell whether the tea or the milk was added first to a cup.

[westcort]

Missed that, but still think commentary on the origin of the 5% rule for p values is of interest.