it might be that simple probability theory is not a good vehicle for
talking about the error(S) that can/have occurred in the election (like
florida) but, the reality is that we know for sure that there are several
sources of error that can and do occur
1. voter error (misplaced marks, accidental double marks, FORGotten marks,
etc.)
2. machine error (NO machine is perfect in accounting for the marks made by
voters and what the tallies turn out to be ... even ETS will tell you that
for optical scan scoring of answer sheets)
3. hand recount errors ... the eye may or may NOT be mightier than the
machine ... but, human recount errors do occur (even if there are 5 people
looking at the same set of ballots)
4. misc errors ... like, as the truck goes to tallahassee, do we know for
sure that ALL the cast ballots are in the ryder truck ... ballots are lost
in a variety of ways .... or, misleading and confusing ballots ...
etc. etc.
now, there are at least three separate issues here
A. to what extent can we quantify the volume of any/all of the above kinds
of errors?
B. to what extent are these errors independent of one another?
C. how, if at all, do any/all of these errors impact on the TRUE count of
the ballots?
At 12:57 PM 11/30/00 +0000, Gene Gallagher wrote:
>There seems to be some misunderstanding in the press about a fundamental
>difference between a sample of a larger population and a complete
>census.
dennis roberts, educational psychology
penn state university, 208 cedar building
university park, pa USA 16802 ... AC 8148632401
[EMAIL PROTECTED] ... http://roberts.ed.psu.edu/users/droberts/drober~1.htm
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================
