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 #65: Which raw data? [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
Blue22 Donating Member (42 posts) Send PM | Profile | Ignore Wed Mar-02-05 07:44 AM
Response to Reply #64
65. Which raw data?
Which raw data are you referring to? In this thread we are essentially working with three sets: 1) actual county canvas results of the 11/2004 general election in each precinct, 2) the Mitovsky-Edison exit-poll survey results grouped into precincts, and 3) demographic characteristics of each election precinct from census data. We are trying to use the census demographic data as a bridge to cross-walk the exit-poll precincts to the actual canvas precinct results. Minvis has already identified one of the 49 precincts in the exit-polls using only population and vote result characteristics from the two different groups. We have simplified the match by concentrating on only a few congressional districts. In the case of CD1 we have three exit-poll results that are within a group of 967 voting precincts in CD1. The daunting task of matching a single exit-poll precinct to the voting precincts is simplified by eliminating voting precincts based on obvious differences with the exit-poll voting results. For instance, when trying to match an exit-poll precinct where Kerry received 85 percent of the sample to the voting precincts, we can just focus on the 30 or so precincts where Kerry received 75 to 95 percent of the vote. Then out of the thirty precincts in this group we can use other demographic characteristics to rule out other precincts. So the match becomes simpler and simpler. In the end, we will have pretty good guesses about which voting precincts and exit-poll precincts match, but we will never be 100 percent certain. Then we can start looking for differences between the poll vote and actual vote and ask how that could have happened. Minvis already matched one exit-poll and precinct. We probably don't even have to match all 49 precincts in the Ohio exit-poll because we already know the precincts where the big discrepancies occurred between what Mitovsky expected for that precinct before the election and what happened in the 'official' recorded vote. As Minvis summarized, Mitovsky was tripped up in CD1, CD2, CD8, CD9 and CD13. So we're going to focus our energies in these.
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