Chronology | Current Month | Current Thread | Current Date |
[Year List] [Month List (current year)] | [Date Index] [Thread Index] | [Thread Prev] [Thread Next] | [Date Prev] [Date Next] |
On Feb 21, 2014, at 9:45 PM, "Ian Sefton" <I.Sefton@physics.usyd.edu.au> wrote:
On 21/02/2014, at 12:49 AM, Jeffrey Schnick wrote:
So far the only general law of human behavior we've seen asserts that
people "religiously avoid" consecutive numbers when cooking up numbers ...
I wouldn't call it a law but I was operating on the hypothesis that in trying to cook up a random distribution of numbers people tend to shy away from nice round numbers like 10, 20, and 30.
...
I was thinking along the same lines (although I think "religiously" is a bit of an exaggeration).
So I used the good old chi-squared null-hypothesis thing to check out the following hypotheses:
1) People will tend to avoid numbers evenly divisible by 5 (which includes the next case)
2) People will tend to avoid numbers evenly divisible by 10.
3) People may be biassed in favour of (or against) primes.
I also checked a couple of other ideas but did not discover anything.
Results:
1) List 1: p = 0.0034; list 2: p = 0.81. We may be on to something here.
2) List 1: p = 3.560E-06 (wow!); but wait for it ... list 2: p = 0.019 (which lies within the traditional 5% boundary).
3) Exactly the same distribution of primes/non-primes occurred in both sets but there is nothing to get excited about; p = 0.69 in both cases.
Given that only one of the data sets was generated by people alone, I'm betting that was list 1. I am also suspicious that the generator of list 2 may not be truly "random".
Cheers
Ian
_______________________________________________
Forum for Physics Educators
Phys-l@phys-l.org
http://www.phys-l.org/mailman/listinfo/phys-l