Skip to main content

View Diary: Retired NSA Analyst Proves GOP Is Stealing Elections (203 comments)

Comment Preferences

  •  I've seen this evidence before (0+ / 0-)

    It doesn't make any sense.  Romney did better in different districts and worse in others?  You don't say?  People believe different things in democracies?  Really?  I can't imagine.

    •  to be fair, it's correlation, not just variation (0+ / 0-)

      They weren't expecting Romney's vote share to covary with the number of votes cast. And they couldn't find a specific measured variable that would "explain" the correlation.

      That isn't likely to surprise many people who study election data, because we're used to having our data be inadequate to our riddles. But these guys apparently were predisposed to jump to a conclusion. I think their story is worth considering, but I cannot make it make sense.

      What happened with exit polls after 2004 was kind of similar. Some folks still insist that the exit poll discrepancies are prima facie evidence of fraud unless someone can explain specifically why they were larger in some states than in others. Well, if I had had cameras trained on all the interview sites, maybe I would be able to do that. In real life, I can say that (1) the exit poll results in many states don't make sense on their face, and (2) the exit poll results aren't correlated with things I would expect them to be correlated with if they were appreciably measuring fraud. As an empiricist, I think that's pretty much the end of that story. But lots of people either aren't trained as empiricists, or perhaps aren't attuned to the quirks of this field, or just are wedged in their predispositions.

      Election protection: there's an app for that! -- and a toll-free hotline: 866-OUR-VOTE
      Better Know Your Voting System with the Verifier!

      by HudsonValleyMark on Fri Oct 26, 2012 at 04:55:04 PM PDT

      [ Parent ]

Subscribe or Donate to support Daily Kos.

Click here for the mobile view of the site