On Nov 10, 2004, at 4:44 PM, Gautam Mukunda wrote:
--- Warren Ockrassa <[EMAIL PROTECTED]> wrote:Three percent (51:48) is not, by any definition of the term, a substantial majority. As it happens, three percent is within the margin of error for most statistical purposes. Fact check, indeed.
Warren, _an election is not a sample_.
Strewth -- and yet, many seem to see fit to take a 51% majority as a "mandate", suggesting that the election is in fact a sample. That there are 51%, IOW, who were surveyed and spoke out plainly in support of a given administration (any administration) and, by implication, everything they see fit to stuff under the umbrella of that administration.
That is, election results in this nation often seem to be interpreted precisely as though they were surveys.
But that's tangential; I was merely pointing out that a three percent difference is not only not a "substantial" majority; it's barely recognizable at all. It could even be within the margin of error for discarded, destroyed or otherwise invalidated votes.
"The margin of error" refers to the chance that the mean of a statistical sample of a population differs from the true mean of a population. But an election is not a sample. An election is an enumeration of the entire universe - all votes.
Actually an election is an enumeration of the universe of votes, but not of the entire universe itself.
-- Warren Ockrassa, Publisher/Editor, nightwares Books http://books.nightwares.com/ Current work in progress "The Seven-Year Mirror" http://www.nightwares.com/books/ockrassa/Flat_Out.pdf
_______________________________________________ http://www.mccmedia.com/mailman/listinfo/brin-l