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 #49: is this a "serve"? [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
OnTheOtherHand Donating Member (1000+ posts) Send PM | Profile | Ignore Mon Aug-22-05 02:33 PM
Response to Reply #45
49. is this a "serve"?
OK, here are some numbers on my laptop. Nothing sacred about them.

Currently working with 94.0% turnout among Gore2K and Bush2K voters, 97% among Other2K voters -- gives a decent number of DidNotVote2K voters under my other assumptions.

So: I've got

Gore 2000 46.275M 84.83% Kerry, 14.63% Bush
Bush 2000 45.782M 7.20% Kerry, 92.31% Bush
Other 2K 3.701M 65.90% Kerry, 18.10% Bush
DNV 2K 26.535M 52.90% Kerry, 46.50% Bush

which yields, within a few hundred, the official result of Bush winning by about 3 million votes.

Then downstream I have a pro-Kerry "response bias" on the order of 1.12 to give Kerry a 3% margin in the national exit poll.

I further have some estimates, inspired by the 2000-04 NES panel, of false recall. For instance, I observe that among panel participants who said in 2000 that they had voted for Gore, 7.3% said in 2004 that they had voted for Bush in 2000. In this group, 26% said they voted for Kerry, and 65% said they voted for Bush. The sample is small, but hey, it's a starting place, so I use those proportions. (I similarly assume, also based on the panel, that 1.6% of Bush2K voters false-recall themselves as Gore2K voters, and this group breaks 95/5 for Kerry. In the actual panel, there were only 5 such people, and they all voted for Kerry.)

I end up with the final results for the unweighted exit poll:

reported Gore2K voters, 38.8%, of whom 90.3% Kerry, 9.2% Bush
reported Bush2K voters, 40.2%, of whom 9.3% Kerry, 90.3% Bush
reported Oth2K voters, 3.3%, of whom 69.2% Kerry, 17.0% Bush
reported DNV2K voters, 17.6%, of whom 56.1% Kerry, 43.2% Bush

all reasonably close to the actual unweighted exit poll results -- I am low on reported DNV2K voters (18.4% in the actual unweighted results). The actual unweighted results show Bush2K voters outnumbering Gore2K voters by only about 1.1%. (But, by assumption, Kerry voters -- many of whom were Gore2K voters -- are overrepresented in the exit poll. Downweighting the Kerry voters to compensate should yield a reported Bush2K/Gore2K split close to the 43/37 margin in the official results.)
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