[R] re cognizing patterns

mel mel at altk.com
Tue Feb 12 19:13:23 CET 2008


Paul Artes a écrit :

> DeaRs,
> i'm looking for some references on a statement as follows:
> "Humans are good at spotting trends and patterns in data, but they are also
> good at spotting those patterns where none really exist". This is not
> verbatim but there must be some scholarly work on this. I can't remember
> where I came across it - perhaps I dreamed it up? Help, anyone?

our eyes have some tendency to believe that
randomness <=> equiprobability.
And by contraposition, non-equiprobability <=> non-randomness.

quite easy to see "a posteriori" patterns in
non-equiprobable, but alas perfectly random, samples.

In french, in 2D this effect is sometimes called "effet rateau".



More information about the R-help mailing list