- I have to disagree -
On Sat, 23 Dec 2000 03:22:56 -0800, Jake <[EMAIL PROTECTED]>
wrote:
> This year, circumstances dictated that the US Presidential race boiled
> down to the results in Florida. That's where the decisive Electoral
> Votes were and that's where the outcome was most uncertain. Since then,
< snip ... >
> Most of us feel that we know what "margin of error" means but to make
> sure we're all on the same page, let's review.
>
> "Margin of error" is a term out of survey polling that refers to the
> confidence we have in the results of a given survey. In general, the
> margin of error corresponds to the 95% confidence interval. For example,
> if a pre-election survey indicates that 49% of "likely voters" want
> Bush, 47% want Gore and 4% want neither, but the margin of error is
< snip, rest >
You have defined one sort of error, one sort of margin.
Statisticians - I hope you are not one - should be aware of other
sources of error.
There is measurement error. And for this circumstance, we could
call another important source, "instrumental error." Or, "counting"
error.
Can a group of amateurs feed 2 million cards through machines
and come up with exactly the same count? No.
(And then there are the 4 million votes by other methods.)
Can they come within a consistent 200 vote margin for one candidate?
Probably not. The automatic-recount triggered by the election
falling within 30,000 votes reduced Bush's apparent lead by about
1500 votes, just on trying to clean up the tabulations.
That fixed some gross errors, arithmetic and others;
a straight-forward recount like the first would come much
closer to being a good replication, but it would not be perfect.
200? Maybe 500, plus or minus. This is the margin-of-error Reality.
And that does not even take into consideration the arbitrary
judgments that ought to be made on 10% or more of the180,000
not-counted ballots, two-thirds of which are over-votes.
IF there is a definitive answer in the ballots, it would have to show
up, I think, as one candidate gaining a lead of several thousand
from among the not-counted, once the assorted errors should
be categorized, IF there were agreement on where to draw the line.
(That winner would be Gore, from all the evidence I have read)
--
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/
=================================================================
