Re: STATISTICAL THOUGHT IN THE SOCIAL SCIENCES Pt. II

From: joedees@bellsouth.net
Date: Mon 23 Dec 2002 - 18:16:22 GMT

  • Next message: Keith Henson: "Re: Memes and evolutionary psychology"

    >
    > >When perusing whether and to what degree an existent
    > (I'll just substitute 'item' where ever I see 'existent')
    >
    >
    > > such as a behavior
    > >or belief facilitates or hinders niche occupation in a spectrum of
    > >variable environments (and the prevalence and concommitant social
    > >benefit or superfluity of a particular behavior or belief is part and
    > >parcel of the memetic environment), a fitness landscape is indeed a
    > >better representation, but when simply perusing the spectrum of
    > >occurrence of a particular existent, such as manifestation of a
    > >particular behavior pattern or belief in a certain concept, where
    > >some percentage is likely to manifest such a behavior or hold such a
    > >concept more than others and less than still others, the Bell curve
    > >is the most Occamically efficient faithful representation of such a
    > >statistical spread.
    >
    > No. I think that if you want to describe what percentage of a
    > population has a certain belief as opposed to another then a bell
    > curve would not be appropriate unless you have gathered statistical
    > evidence that a bell curve is the appropriate distribution for that
    > belief. A two dimension array such as you were describing would also
    > imply a range of behaviors along a scale and not just the percentage
    > of one behavior. Such a range would have to have linear relationship
    > so that one item differed from the other in such a manner that one
    > could be said to 'increasing' from another and that another was
    > 'decreasing'. The advantage of a multidimensional array is that there
    > doesn't have to be a continuum of increasing or decreasing
    > relationships between items.
    >
    Bell curves do not have to be shaped like bells; they can be skewed to reflect the aggregate data they represent. Thus, whatever the statistical distribution, the Bell curve works.
    >
    > I couldn't find 'Occamically' . I think Occam would have preferred
    > that you use 'simplistically'.
    >
    > Ray
    >
    >
    > > >
    > > > Ray Recchia
    > > >
    >
    >
    > ===============================================================
    > This was distributed via the memetics list associated with the
    > Journal of Memetics - Evolutionary Models of Information Transmission
    > For information about the journal and the list (e.g. unsubscribing)
    > see: http://www.cpm.mmu.ac.uk/jom-emit
    >

    =============================================================== This was distributed via the memetics list associated with the Journal of Memetics - Evolutionary Models of Information Transmission For information about the journal and the list (e.g. unsubscribing) see: http://www.cpm.mmu.ac.uk/jom-emit



    This archive was generated by hypermail 2.1.5 : Mon 23 Dec 2002 - 18:16:58 GMT