[EMAIL PROTECTED] (Donald Burrill) wrote in message
news:<[EMAIL PROTECTED]>...
> So far all responses have appeared to assume that the data represent
> left and right ovaries on the SAME women. But this cannot be the case,
> because the total number of left ovaries in the data is 132, and of
> right ovaries 103. [...]
Here are the two different interpretations that I suggested for the
data. Neither one is ruled out by the information that was given.
Unmatched data: 132 women with pathology in the left ovary only, and
103 other women with pathology in the right ovary only. The row and
column labels 0,1,2,3,4 are the degrees of severity of the pathology.
Women with pathologies in both ovaries are excluded, as are women
with no ovarian pathology.
RIGHT
0 1 2 3 4 Total
L 0 - 66 28 6 3 103
E 1 91 - - - - -
F 2 31 - - - - -
T 3 7 - - - - -
4 3 - - - - -
Total 132 - - - - -
Matched data: women with pathologies in both ovaries are Xs;
the 132 women with pathological left ovaries are Ls & Xs,
the 103 women with pathological right ovaries are Rs & Xs.
There are 132-103=29 more Ls than Rs. If there are no Xs
then this case reduces to the first interpretation.
RIGHT
0 1 2 3 4 Total
L 0 - R R R R -
E 1 L X X X X 91
F 2 L X X X X 31
T 3 L X X X X 7
4 L X X X X 3
Total - 66 28 6 3 103\132
.
.
=================================================================
Instructions for joining and leaving this list, remarks about the
problem of INAPPROPRIATE MESSAGES, and archives are available at:
. http://jse.stat.ncsu.edu/ .
=================================================================
