On Wed, 26 Mar 2003, kjetil brinchmann halvorsen wrote:
> On 26 Mar 2003 at 10:55, Rich Ulrich wrote:
>
> > On Wed, 26 Mar 2003 13:18:17 +0100, "david" <[EMAIL PROTECTED]> wrote:
> >
> > > I would like to know a measure for testing the binormality of a
> > > data set.
> >
> > I don't use the term, binormal.
> > And Google turns up something concerning topology,
> > which is not a usual topic in these groups.
> >
> > Are you referring to bivariate normality?
>
> What is the wrong with the word binormal?
I don't suppose there's anything _wrong_ with it, as a word; it's just
that I (for one) do not know what the querent wants to mean by it.
Possibly he intends, as Rich guesses, "bivariate normality"; but the
word "binormal" is quite unfamiliar to me in any _statistical_ context.
My Random House Dictionary of the English Language supplies only one
definition for "binormal", from geometry:
"the normal to a curve, lying on the osculating plane at a
given point in the curve"
-- and this is a noun, not an adjective. This seems not to be what the
querent had in mind, since in his terms "binormality" (an unnecessary
noun suffix, "-ity", if "binormal" is already a noun) is a quality
associated with a data set.
I learned "normal" meaning "perpendicular" long before I ever
encountered "normal" as a synonym for "Gaussian", referring to a
distribution. Using "normal" for a distribution seems to me to be just
begging for misunderstanding: among mathematicians and engineers, who
quite reasonably fail to see much in the way of perpendicularity in the
distribution in question; and among psychologists, with their tendency
to consider anything _not_ normal as "abnormal" or perhaps "subnormal",
neither of which can be said to be particularly well-defined terms even
in their contexts, and which have no meaning at all in any statistical
(or probabilistic) context.
-----------------------------------------------------------------------
Donald F. Burrill [EMAIL PROTECTED]
56 Sebbins Pond Drive, Bedford, NH 03110 (603) 626-0816
.
.
=================================================================
Instructions for joining and leaving this list, remarks about the
problem of INAPPROPRIATE MESSAGES, and archives are available at:
. http://jse.stat.ncsu.edu/ .
=================================================================
