But as someone pretty well-versed in statistics, I'm not aware of any statistical procedure that could separate randomness or simple error probability from the following claim:
The culture of science, at its purest, is one of freedom in which any idea can be tested regardless of how far-fetched it might seem. “I don’t believe in anything Bob is doing, but I support his right to do it,” said Will Happer, a professor of physics at Princeton.
Though it's a bit more complicated than this from a statistical perspective, and you have to differentiate "statistical significance" and "practical significance": If you flipped a coin 10,000 times, how shocked would you be to get 5002 heads and 4998 tails?
Analyzing data from such trials, the PEAR team concluded that people could alter the behavior of these machines very slightly, changing about 2 or 3 flips out of 10,000.
First posted at Psyche Killer qu'est que c'est on 2/13/07