RE: Design detection and minimum description length

From: Alexanian, Moorad (alexanian@uncw.edu)
Date: Sat Nov 23 2002 - 17:16:08 EST

  • Next message: Michael Roberts: "Re: Agnosticism: Sondra Brasile's comments"

    In science what we detect is data that is determined purely by
    physical devices, which gives us the subject matter of science.
    Everything else is human inference, for instance, the notion of
    design. Once one introduces the notion of function, e.g., the notion
    of survival in natural selection, then one is dealing with design.
    Moorad

            -----Original Message-----
            From: Stein A. Stromme [mailto:stromme@mi.uib.no]
            Sent: Sat 11/23/2002 2:32 PM
            To: asa@calvin.edu
            Cc:
            Subject: Re: Design detection and minimum description length

            [Iain Strachan]

            | Suppose you send me 10 pairs of points (x(i), y(i)) for i=1 to 10.
            | You don't tell me anything about whether it's designed or not
            | designed.
            |
            | I claim that I can tell you if there is a correlation between the
            | variables (for "correlation" read "design") simply via the
            | methodology of using Minimum Description Length. If I find such a
            | correlation, it is useful to me because I can interpolate between the
            | specified x(i) points to make new predictions from my model. Here's
            | how I do it.

            You detect "correlation", which is hardly surprising, but what is the
            connection to "design"?

            Stein
            --
            Stein Arild Str¬Ømme +47 55584825, +47 95801887
            Universitetet i Bergen Fax: +47 55589672
            Matematisk institutt www.mi.uib.no/~stromme
            Johs Brunsg 12, N-5008 BERGEN stromme@mi.uib.no

    This archive was generated by hypermail 2.1.4 : Sat Nov 23 2002 - 19:13:04 EST