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 #109: Sigh [View All]

Printer-friendly format Printer-friendly format
Printer-friendly format Email this thread to a friend
Printer-friendly format Bookmark this thread
Home » Discuss » Topic Forums » Election Reform Donate to DU
Febble Donating Member (1000+ posts) Send PM | Profile | Ignore Thu Oct-09-08 01:43 PM
Response to Reply #22
109. Sigh
The raw data were released. They always are. They were even free online for a year. I downloaded them myself.

What wasn't released were the precinct vote totals, because that would have meant the precincts could have been identified, and thus compromised the confidentiality of the respondents. However, "blurred" totals were released for Ohio, and more could have been commissioned. But weren't. The most likely reason being that it was pretty apparent from the Ohio data set that they weren't very informative.

However, as you know, I had access to the unblurred numbers, because I reanalysed them for Mitofsky. And my most important finding was released into the public domain by Mitofsky himself. This was the finding that the precinct level discrepancy was completely uncorrelated with advantage to Bush. It is extremely difficult to see how this could possibly be consistent with widespread electronic fraud.

And at precinct level, the data is far too noisy to tell you whether any one precinct was fraudulent. It only makes sense if you analyse a large number of precincts (and there are only tens of precincts polled in each state - Ohio was worth looking at because there were a relatively large number: 50. Still a tiny number for useful statistics.

Gary, exit polls are simply a very poor way of checking on the vote count. They don't tell you what you want to know. They have sensitivity but no specificity. They are unlikely to match the count if the count is fraudulent, but they are perfectly capable of not matching the count even it the count is correct. They are likely to be particularly misleading in an election conducted in an atmosphere of distrust.

What is required is diligent oversight, and you can do this, this time, even where audits aren't mandatory. Make sure the precinct totals, where available, match the county tabulations, and if not, find out why not. Be observers at precincts. Debrief voters leaving the precinct on any troubles they might have had. Collect data, including anecdotes (data may not be the plural of anecdote, but many anecdotes amount to data).

But exit polls are not what you want here. Tests that give false positives are as useless as tests that give false negatives.
Printer Friendly | Permalink | Reply | 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