If we want to know covariance from 2*2 Table, how many samples are needed at least.

Thanks a lot



[EMAIL PROTECTED] (Donald Burrill) wrote in message news:<[EMAIL PROTECTED]>...
> On 22 Aug 2003, Eric Bohlman wrote in part:
> 
> >   But mathematically, that's nonsensical;  zero correlation implies a
> > roughly circular pattern of points
> 
> While a circular pattern implies zero correlation, the converse is not
> true.  A horizontal (or vertical) line also implies zero correlation.
> So, for that matter, does the symmetrical center section of a parabola.
> and any number of other patterns:  think of all the patterns described
> by a set of orthogonal polynomials.  "Zero correlation" of itself does
> not imply ANYthing about the pattern described by the bivariate space,
> except that the sum of products of deviations from the means of the two
> variables is zero -- which can happen in an infinite number of ways,
> arising from an infinite number of possible patterns.
> 
> > (I like Stephen Jay Gould's heuristic that correlation measures the
> > "skinniness" of a scatterplot),
> 
> Which is true enough for the usual rather amorphous scatterplot that
> the term "scatterplot" conjures up in one's mind, AND where the
> "skinniness" in question is tilted (NOT horizontal, NOT vertical).
> 
> > and it's rather obvious that if you simply interchange axes, there's
> > no difference between the two situations.
> 
> Precisely.
> 
> > I think this is a case where we're encountering what Sir Francis
> > Bacon called an "idol," a prejudice of thought that distorts our
> > view of reality.  We want to believe that correlation is defined for
> > any pair of random variables, but in fact it's meaningless if one of
> > those RVs has all its density concentrated at a single point.  We
> > somehow expect that because we call it a random "variable" it has to
> > *vary*, but the definition of a random variable is merely "a
> > function whose domain is a probability space"  and constants meet
> > that definition.
> 
> More than that, though:  correlation is defined whether the variables in
> question are random or not.
> 
>  -----------------------------------------------------------------------
>  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/                    .
> =================================================================
.
.
=================================================================
Instructions for joining and leaving this list, remarks about the
problem of INAPPROPRIATE MESSAGES, and archives are available at:
.                  http://jse.stat.ncsu.edu/                    .
=================================================================

Reply via email to