At Gödel’s Lost Letter and P=NP, Ken Regan tackles what the statistical nuance of 'evidence' means in the latest Higgs disclosure, delving into statistics and social convention in a hard science (actually, he puts "hard science" in quotes, though I am not sure why - perhaps he thinks 'hard' is the colloquial version, like 'difficult' so he doesn't want to annoy social fields) such as particle physics and whether the assumptions behind the confidence intervals can be violated on both sides: by humans owing to unexpected selection bias, and by Nature possibly acting like a cheating prover in an interactive protocol.
Tommaso Dorigo will like the article because he also relates statistical analysis using chess examples of the Littlewood and Look-Elsewhere problems:
"Rumor has it that the ATLAS team will claim a 3.5 sigma deviation, and the CMS team will claim about 2.5 sigma. These would aggregate to about 4.3 sigma if the results are independent. Whether independence holds between them is being argued, but we have a more basic question first: Where did the value(s) of “sigma” come from?"
Because a rare event brings with it its own new set of problems even knowing what sigma might mean.
The Higgs Confidence Game - K.W. Regan
