Skip to main content

View Diary: Daily Kos Elections Weekly Open Thread: Saturday Edition (521 comments)

Comment Preferences

  •  Was Obama up 10 in the spring? (1+ / 0-)
    Recommended by:

    Was Romney up 4 in October? I really doubt it.

    •  So then what changes? (1+ / 0-)
      Recommended by:

      What about their methodology makes it inaccurate and then accurate?  That's not a rhetorical question.

      27, Dem, Dude seeing a dude, CT-04(originally), PA-02/NY-14 (formerly PA-02/NY-12).

      by Xenocrypt on Sun Nov 11, 2012 at 11:58:43 AM PST

      [ Parent ]

      •  My guess (2+ / 0-)
        Recommended by:
        DCal, MichaelNY

        is just random variance, and they were lucky that their most accurate poll was their last one.

        But if we need some fancier explanation than that... maybe it becomes easier to identify the folks who are most likely to vote as you approach the election, and earlier polls are more likely to over-react to temporary shifts in momentum? That would sort of fit Pew's pattern this year, where when they missed they tended to miss in the direction of the candidate who had the more energized supporters at the moment.

        •  I don't think it luck at all (2+ / 0-)
          Recommended by:
          MichaelNY, itskevin

          Considering they've now basically nailed the last three presidential elections. Nobody can match that. They also did better than anybody but Ipsos on the 2010 generic House ballot.

          But just as their final poll is always accurate they do seem particularly sensitive to swings throughout the year. It was very much like that in 2004 as I posted the night of "Romney +4 in Pew - Arghhhhhhhhhhhhhhh."

          "What do you mean "conspiracy"? Does that mean it's someone's imaginings and that the actual polls hovered right around the result?" - petral

          by conspiracy on Sun Nov 11, 2012 at 01:39:51 PM PST

          [ Parent ]

Subscribe or Donate to support Daily Kos.

Click here for the mobile view of the site