[7933] in cryptography@c2.net mail archive
RE: human failings question
daemon@ATHENA.MIT.EDU (Kristen Tsolis)
Fri Oct 6 01:52:05 2000
From: "Kristen Tsolis" <ktsolis@mindspring.com>
To: <honig@sprynet.com>
Cc: <feferman@math.princeton.edu>, <coderpunks@toad.com>,
<cryptography@c2.net>
Date: Thu, 5 Oct 2000 17:31:11 -0700
Message-ID: <LPBBJMDPAKJKJBKLMHOGMEDCCEAA.ktsolis@mindspring.com>
MIME-Version: 1.0
Content-Type: text/plain;
charset="iso-8859-1"
Content-Transfer-Encoding: 7bit
You're probably referring to the Wald-Wolfowitz runs test. As David
mentioned, studies that have used this test note that people tend to
over-oscillate between two values and under-produce longer runs like
1,1,1,1,1.
Nina, you may find what your looking for by doing a google search on
"Wald-Wolfowitz runs test". for more info on the test, see here:
http://home.clara.net/sisa/ordhlp.htm
>I have no specific ref in mind, but I do remember that humans
find long runs (e.g., 01011000000110) unrandom, when asked to
pick one excerpt vs. another. There was a
recent paper on the perception of 'lucky streaks' in basketball,
which unearthed their superstitious nature (ie an artifact of learning
algorithms, like randomly-reinforced pigeons' "superstitions").
So come to think of it, there are more papers on (mis)perceiving randomness
than on (mis)generating it.
