In article <[EMAIL PROTECTED]>,
Radford Neal <[EMAIL PROTECTED]> wrote:
>In article <[EMAIL PROTECTED]>,
>Thom Baguley <[EMAIL PROTECTED]> wrote:
>>I admit to being confused by Radford's analysis. Radford, is your point that
>>if there are a large proportion of "empty/no vote" ballots then we would
>>expect them to be decided close to 50:50 and hence shift the balance from
>>30:70? I think this depends on the counting procedure. If I were in charge I'd
>>have a "no vote" category where all "I'm not sure" ballots would be placed. If
>>this happened, assuming no bias we'd expect the original 30:70 ratio or
>>thereabouts (as observed).
>I assume that they do have a "no vote" category. But one wouldn't
>expect that all real "no votes" get put in that category. Some must
>get counted as votes. If the procedure is unbiased, the ballots that
>are actually "no votes", but that are counted as votes should split
>equally. Plus, there are the ballots that actually were meant as
>votes, but which are misassigned.
Having seen the pictures of the "butterfly" ballot, there
are many other candidates as well. Not all counties used
that particular one, but they all have many candidates.
However, here is one place where I would expect inadvertent
bias on the part of those assessing the ballot "manually"
to show up. This makes the process quite subject to human
error, even if there is no intentional error. We have had
reports of one person claiming a vote intention, and others
claiming that it was nothing of the sort.
--
This address is for information only. I do not claim that these views
are those of the Statistics Department or of Purdue University.
Herman Rubin, Dept. of Statistics, Purdue Univ., West Lafayette IN47907-1399
[EMAIL PROTECTED] Phone: (765)494-6054 FAX: (765)494-0558
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================
