Rasmussen explains

  • MusclFurPeX

    Posts: 166

    Nov 12, 2012 3:32 AM GMT
    Rasmussen Reports, the prolific automated pollster whose projections fell far from the mark Tuesday, explains what went wrong:

    Our final daily presidential tracking poll showed Romney at 49% and Obama at 48%. Instead, the president got 50% of the vote and Romney 48%. We were disappointed that our final results were not as close to the final result as they had been in preceding elections. There was a similar pattern in the state polls. For example, in Ohio we projected a tie at 49% but the president reached 50% of the vote and the challenger got just 48%. Although every individual result in the battleground states was within the margin of error, the numbers we projected were consistently a bit more favorable for Romney than the actual results.

    A preliminary review indicates that one reason for this is that we underestimated the minority share of the electorate. In 2008, 26% of voters were non-white. We expected that to remain relatively constant. However, in 2012, 28% of voters were non-white. That was exactly the share projected by the Obama campaign. It is not clear at the moment whether minority turnout increased nationally, white turnout decreased, or if it was a combination of both. The increase in minority turnout has a significant impact on the final projections since Romney won nearly 60% of white votes while Obama won an even larger share of the minority vote.

    Another factor may be related to the generation gap. It is interesting to note that the share of seniors who showed up to vote was down slightly from 2008 while the number of young voters was up slightly. Pre-election data suggested that voters over 65 were more enthusiastic about voting than they had been four years earlier so the decline bears further examination.

    As mea culpas go, this one is a little thin. While Rasmussen wasn’t alone in misreading the composition of the 2012 electorate and it’s true that all the firm’s battleground state polls were within the 4-point margin of error, there are a few clunkers in there. In Wisconsin, for example, Rasmussen was the only public pollster reporting a 49-49 tie -- in the final two weeks, the five other pollsters in the field there pegged Obama’s lead between 3 and 9 percentage points. The actual result was a 53-46 Obama win.

    Colorado was similarly errant. In the final round of polls, Rasmussen was the one reporting the biggest Romney lead -- 50-47 – but the outcome was 51-46 Obama.

    Rasmussen got a few states right – placing Obama in the lead in Nevada and New Hampshire and Romney ahead in North Carolina – but simply getting the winner correct in 3 of 9 battleground states isn’t going to win over the many detractors who regularly dismiss the firm’s polls for their often overly rosy GOP predictions.
  • TroyAthlete

    Posts: 4269

    Nov 12, 2012 3:35 AM GMT
    There's nothing to explain: Rasmussen sucks and has lost all credibility, not that it had any left except on the hard right. But now even they know he's a joke.
  • Posted by a hidden member.
    Log in to view his profile

    Nov 12, 2012 3:55 AM GMT
    poll_accuracy.png
    One bright spot on this chart: Rasmussen was as bad as NPR. icon_lol.gif
  • Webster666

    Posts: 9217

    Nov 12, 2012 6:05 AM GMT
    Rasmussen Polls have ALWAYS been dismissed as being greatly and consistently skewed towards Republican candidates. They need to learn how to do credible polling, or stop lying about their results.
  • Posted by a hidden member.
    Log in to view his profile

    Nov 12, 2012 6:36 AM GMT
    So can we say, going forward, that when right-wingers tout Rasmussen as more accurate than the other polls, that they should blow it out their asses?
  • GQjock

    Posts: 11649

    Nov 12, 2012 12:33 PM GMT
    When you're a republican leaning poll .... there's no need for explanation

    We know we need to handicap your findings all the time
  • coolarmydude

    Posts: 9190

    Nov 12, 2012 12:58 PM GMT
    Just to clarify for those not reading the graph properly, that solid line down near the center is the actual election result. The polls closest to that line were the most accurate. The National Journal was overstating Obama's lead.
  • Posted by a hidden member.
    Log in to view his profile

    Nov 12, 2012 1:03 PM GMT
    coolarmydude saidJust to clarify for those not reading the graph properly, that solid line down near the center is the actual election result. The polls closest to that line were the most accurate. The National Journal was overstating Obama's lead.

    Important point!
  • TroyAthlete

    Posts: 4269

    Nov 12, 2012 7:59 PM GMT
    coolarmydude saidJust to clarify for those not reading the graph properly, that solid line down near the center is the actual election result. The polls closest to that line were the most accurate. The National Journal was overstating Obama's lead.


    Of course. With the notable exception of NPR, the ones that were most off are either right-wing hack pollsters or associated with right-wing hack news outlets (CNN went full teabagger after Obama bombed the first debate).

    Meanwhile among the most accurate are Daily Kos and PPP.

    If Republicans continue to take FOX News, Rasmussen, Gravis, American Research Group, Newsmax and the Washington Times seriously they will continue to be shocked by reality.