You are viewing an obsolete version of the DU website which is no longer supported by the Administrators. Visit The New DU.
Democratic Underground Latest Greatest Lobby Journals Search Options Help Login

Reply #10: No speculation. Eliminate the impossible, you are left with the truth. [View All]

Printer-friendly format Printer-friendly format
Printer-friendly format Email this thread to a friend
Printer-friendly format Bookmark this thread
This topic is archived.
Home » Discuss » Topic Forums » Election Reform Donate to DU
TruthIsAll Donating Member (1000+ posts) Send PM | Profile | Ignore Tue Feb-22-05 02:26 PM
Response to Reply #8
10. No speculation. Eliminate the impossible, you are left with the truth.
Edited on Tue Feb-22-05 02:57 PM by TruthIsAll
"Am I to believe that Bush was to know in the afternoon of election day that he only needed to stop the recount?"

Did I say that?
Of course not.

But they knew about the Palm Beach Butterfly ballot, and the statewide 110,000 overvotes and the 75,000 undervotes.
They knew about Diebold (Volusia 16,022 vote).
And they knew they had friends on SCOTUS.

2."Because Clinton won handily in 1996, despite the exit poll deviation from the actual. There was no need to massage the exit poll data. They could not steal it."

This does not address the exit poll deviation. Why did they massage the data anyway then TIA? and shouldn't this type of "pristine" data that should be used to compare with the 2004 "pristine" data that you use in you calculations?

Here goes:

Mitofsky has always said that the exit polls have always been adjusted to match the votes - but he claims the votes are always more accurate and therefore must re-weight the "raw" data accordingly. You would think that his pre-designed sample, based on years of experience, would give him accurate numbers from the get-go. The irony is that they do just that. But he still cannot use them.

The real reason for re-weighting the exit poll is never mentioned, but Greg Palast has indirectly provided the answer: The discrepancy between the votes as cast and the votes counted is primarily due to endemic ballot spoilage, mostly in Democratic precincts. And we are talking about millions of votes here.

In other words, ballot spoilage is anticipated, so by definition the exit polls can never match the vote count unless the exit poll "raw" data are adjusted accordingly. Mitofsky does not want to be known as a lousy exit pollster; after all, he has a reputation to uphold. So he matches the exit polls to the actual recorded votes - but under the guise of re-weighting for exit poll error. In a sense, he is right. Exit polls do not agree with the recorded, final vote.
But that does not mean the votes are correct. Of course, as Americans, we have been brought up to think the votes are correct.
How naive of us.

That was then. This is now. The practice of matching the votes continues. We still have natural ballot spoilage. But now there are other anomalies, like touch screens which register Kerry votes for Bush. And missing punched cards.

Mitofsky is just doing what he's always done: assuming the vote counts are "correct" and the exit polls are "raw" and unadjusted. So he continues to match the "bad" exit polls to the "good" votes, even if it means that the final weightings must be changed accordingly (see the final NEP Exit Poll of 13660) .

That's how he goes from the "preliminary" WP 13,047 poll with a 38/35/27 PartyID mix, to the "final" 13660 poll with a 37/37/26 mix. Of course, the component percentages must change as well.

The two sets of exit poll adjustments (the demographic weights and the percentage increase in Bush's share) are a powerful mix.

That's why the "Preliminary" WP poll was correct to begin with: it reflected the voter's true intentions - which the recorded vote did not.

And that is why the Democrats always win in the exit polls but only sometimes win elections.

Just my 2c.
And that of Gauss and Bernoulli.
Printer Friendly | Permalink |  | Top

Home » Discuss » Topic Forums » Election Reform Donate to DU

Powered by DCForum+ Version 1.1 Copyright 1997-2002
Software has been extensively modified by the DU administrators

Important Notices: By participating on this discussion board, visitors agree to abide by the rules outlined on our Rules page. Messages posted on the Democratic Underground Discussion Forums are the opinions of the individuals who post them, and do not necessarily represent the opinions of Democratic Underground, LLC.

Home  |  Discussion Forums  |  Journals |  Store  |  Donate

About DU  |  Contact Us  |  Privacy Policy

Got a message for Democratic Underground? Click here to send us a message.

© 2001 - 2011 Democratic Underground, LLC