OOPS!  Correction! see second line below

another way to phrase that is
for each case find x = (X- X_Xbar) and y = (Y - Ybar)
then multiply x*y (this is called a cross-product).
then find the sum of the crossproducts.

Xbar is x with a bar over it  i.e., the mean

There is a set of parens implicit in the formula segment
 sum (  ( (X-Xbar)* (Y-Ybar) ) )

work from the inside out
first do the subractions of the means from the raw scores (gets
deviations scores)
multiply the deviation scores (gets crossproducts)
then sum the crossproducts


Stephen Clark wrote:

> "janne" <[EMAIL PROTECTED]> wrote in message
> [EMAIL PROTECTED]">news:[EMAIL PROTECTED]...
> > I have a correlation formula I don't get to work. And we must use this
> > formula on the test. Let me give you an example: Let's say X  and  Y
> > are:
> > x    y
> > 1   68
> > 2   91
> > 3   102
> > 3   107
> > 4   105
> > 4   114
> > 5   115
> > 6   127
> > _   ___
> > 28  829
> > _                    _
> > X is =3.5 and Y is =103.625
> >
> > Now to my problem. Look at the formula in this URL:
> > http://www.jannesgallery.com/corr.html.
> > How do I do the first (X-X(with a line above))? I have tried to take
> >         _
> >    X-X
> > 1-3.5=2.5
> > 2-3.5=-1.5
> > 3-3.5=-0.5
> > 3-3.5=-0.5
> > 4-3.5=0.5
> > 4-3.5=0.5
> > 5-3.5=1.5
> > 6-3.5=2.5
> > ________
> > 0
> >
> >
> >
> > As you see the answer is zero. What do I do wrong? and the same with
> > Y-Y(with a line above). It turns out to be zero. Please help me to tell
> > how I should do.
> >
> > Janne
> >
> The sum is:
>
> (1-3.5)*(68-103.625) + (2-3.5)*(91-103.625) + ... + (6-3.5)*(127-103.625)
>
> which, in general, will not be zero.


=================================================================
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