uh-oh, what am I saying ...
On Fri, 27 Oct 2000 14:21:36 -0400, Rich Ulrich <[EMAIL PROTECTED]>
wrote:
< snip, cite >
> No, you have it wrong. Think about the case where the two
> candidates/options add exactly to 100% -- the "4% error" is exactly
> the same 4% for both, since one goes down exactly as much as the other
> goes up. This is "correlation" among the proportions. With a few
There is something to what I just posted, but I think I was not paying
attention--
Take two categories adding to 100%; for the larger to have its CI
above 50%, (for this N) it must run from a mean of 54%. That is your
8 point difference.
(However, I don't believe a poll result is quite *that* bad....)
I am confusing myself. I will let someone else answer further.
--
Rich Ulrich, [EMAIL PROTECTED]
http://www.pitt.edu/~wpilib/index.html
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================
