In reply to my question, David MacKay writes:
You said that can imagine rounding up 9 to 10 – which would be elegant if we worked in base 10.
But in the UK we haven’t switched to base 10 yet, we still work in dozens and grosses. (One gross = 12^2 = 144.) So I was taught (by John Skilling, probably) “a dozen samples are plenty”.
Probably in an earlier draft of the book in 2001 I said “a dozen”, rather than “12”. Then some feedbacker may have written and said “I don’t know what a dozen is”; so then I sacrificed elegant language and replaced “dozen” by “12”, which leads to your mystification.
PS – please send the winner of your competition a free copy of my other book (sewtha) too, from me.
PPS I see that Mikkel Schmidt [in your comments] has diligently found the correct answer, which I guessed above. I suggest you award the prizes to him.
OK, we’re just giving away books here!
P.S. See here for my review of MacKay’s book on sustainable energy.
Pingback: David MacKay sez . . . 12?? « Statistical Modeling, Causal Inference, and Social Science
that explains the 12 but what about the sigma/3? Isn’t this just a version of the much-maligned n=30 rule in all statistics textbooks… except that n=30 corresponds to a “tighter” threshold than 1/3?
Kendall and Stuart say 30.
Is this related to the often mentioned n=(10-20) per predictor in a multiple regression?