I seem to recall it was R.A. Fisher who suggested 0.05 as a measure
of disbelief in the null hypothesis.
Both in lectures to first-year students and to seminars to
professionals I often conduct the following class experiment to
explain why 0.05 is a plausible reflection of how we judge
Aha. Thank you. This explains the mystery a year ago when graduate
students in my nonparametric course were simulating the power of
various tests under different alternatives. On the department's
SPARC 10 with recently installed S-Plus 5.1, they were waiting
"minutes" for output even
