Daily Kos

View Story | 43 comments

  •  Sample sizes ~2300 for PPP v. ~700 I think (0+ / 0-)

    If that is true the numbers in your subsample breakdowns are going to more accurate in the PPP poll.

    The 700 is good for overall prediction but the small subsample breakouts would be dicier.

    by HairOnFire on Mon Apr 21, 2008 at 12:05:27 PM PDT

    •  you have to look at MOE (0+ / 0-)

      not just sample size.

      "This union may never be perfect, but generation after generation has shown that it can always be perfected." - Barack Obama (3.18.08)

      by lapis on Mon Apr 21, 2008 at 12:07:00 PM PDT

      [ Parent ]

      •  MOE of is the point with small sub-samples (0+ / 0-)

        If you start out with a larger sample you can go down to smaller subsamples without having your MOE explode.

        Example with AA

        PPP: 2300*.18 (N=414) (AA) ~MOE=5
        SU:  700*14 (N=93)(AA) ~MOE=10

        So, PPP has a MOE of 5 for their AA numbers of Obama v. Clinton and SU has a MOE OF 10.

        by HairOnFire on Mon Apr 21, 2008 at 12:24:25 PM PDT

        [ Parent ]

      •  MOE is determined by sample size (1+ / 0-)

        Recommended by:
        lapis

        For a 99% confidence level, MOE is about 1.26/sqrt(N), where n is the number of respondents.

        In either case, however, the larger sample size for PPP means that it is more precise (as in repeated polls will give about the same result), but not necessarily more accurate. One obvious case would be the infamous Literary Digest poll that had tens of thousands of respondents and showed Landon easily beating Roosevelt. Obviously, either SUSA or PPP has made a significant methodology error, and we can't tell which one it is at this point.

        John McCain John McCain

        by Michiganliberal on Mon Apr 21, 2008 at 12:24:27 PM PDT

        [ Parent ]

    •  the problem with polling primaries (1+ / 0-)

      Recommended by:
      Adam B

      With the difficulties of figuring out who will vote in primaries, it seems to me that methodology error is probably greater than the random sample (MOE) error.

      You have the power to change America. Yes. We. Can.

      by CA Pol Junkie on Mon Apr 21, 2008 at 12:08:47 PM PDT

      [ Parent ]

View Story | 43 comments