Drexel dragonThe Math ForumDonate to the Math Forum



Search All of the Math Forum:

Views expressed in these public forums are not endorsed by Drexel University or The Math Forum.


Math Forum » Discussions » sci.math.* » sci.stat.math.independent

Topic: New project: certification in statistics
Replies: 17   Last Post: Nov 20, 2000 3:14 PM

Advanced Search

Back to Topic List Back to Topic List Jump to Tree View Jump to Tree View   Messages: [ Previous | Next ]
Rich Ulrich

Posts: 1,234
Registered: 12/6/04
Re: manual recount - of punched ballots
Posted: Nov 13, 2000 12:14 PM
  Click to see the message monospaced in plain text Plain Text   Click to reply to this topic Reply

On Sun, 12 Nov 2000 23:45:39 GMT, Ron Hardin <rhhardin@mindspring.com>
wrote:

< snip >
> Say punched cards have a 5% reject rate, a figure I've heard several
> times, then a manual count without bias always raises the totals
> in proportion to the existing votes. Thus as you say, a Democratic
> county manually counted picks up net Democratic votes.
>
> Would you say that therefore a Republican county with the reversed
> numbers ought to be manually counted as well, if a Democratic one
> is? Otherwise it would seem a net Democratic gain is guaranteed.
> The county that hand counts wins an even election.


My newspaper did not tell me whether it was punched cards at fault,
but an article on Sunday remarked that Duvall County
(3-2 Republican) had 26K invalidated votes out of 260K cast.
That is 10%, even higher than the 8% in Palm Beach County this year.
I don't think I have seen any detail at all about Duvall.

I thought that the manual count ought to be detecting loose chad.
I don't know if that would apply in Duvall.
And I am less sure about what the "voting inspectors" are doing, after
seeing a few TV shots.

The "chad" problem seems to account for about half of 10K
blank-votes. Let us assume that in Palm Beach County, 5K or so
(1.1%) intentionally marked no choice for President. That seems to be
a conventional amount, and it is consistent with the 47 additional
votes found in the 1% sample (with a 19-vote margin for Gore).

The last "official" vote-tally I heard was 288 (on CBS, from <?>),
Bush's lead down from 325 (reported by AP). Here are some future
estimates I consider reasonable: Gore gains 1500 from manual counts
in Palm Beach County, and Bush gains 900 in Duvall County and another
300 from absentee ballots, and that puts the total near to ZERO -- at
competition to the New Mexico margin which I last heard as 17.

Well, there were 4 Fla. counties being mentioned for counts, and I
don't mention the other two because I know even less about them.

>
> The benefit of the machine counts is the avoidance of bias. The
> sign of the difference at the end of it all is an excellent estimate,
> not biased, though the totals are biased low by machine counting.
>
> A hand count improves the totals but ruins the differences. But what
> you want is the differences, ie the winner, not the totals.
>
> I have heard that punch cards are favored because they retain
> vote privacy, and they consider the 5% drop rate acceptable.


Someone reported that MA (Massachusetts) quit using punched cards
after a disputed election.

I think that politicians who try to defend a future 5% *error* rate
will find themselves replaced in the next elections.
--
Rich Ulrich, wpilib@pitt.edu
http://www.pitt.edu/~wpilib/index.html





Point your RSS reader here for a feed of the latest messages in this topic.

[Privacy Policy] [Terms of Use]

© Drexel University 1994-2014. All Rights Reserved.
The Math Forum is a research and educational enterprise of the Drexel University School of Education.