..."If you’ve been trying to follow the Presidential election polls lately, you undoubtedly have observed that various polls are moving in different and contradictory directions each day. Some polls show a narrowing race - - today’s CNN headline, for example, reads CNN Poll: Race May Be Tightening. Indeed, today’s GWU-Battleground tracking poll puts the race at 48% to 47% - - a virtual dead heat.
On the other hand, today’s NBC/WSJ poll puts the race at Obama +10, while the ABC/Washington Post poll has Obama +9. Yet the Rasmussen Daily Tracking Poll has the race at Obama +4 for the second day and reports, “The race has remained very stable over the past month.”
So there you have it. Our wonderful, expert polling organizations have determined, with all of the accuracy and impartiality that modern statistical science and polling techniques can muster, that (1) the Presidential race is tightening while (2) Obama is pulling away and (3) the Presidential race remains remarkably stable.
Well, keep in mind that American novelist Samuel Clemens (a/k/a Mark Twain) wrote, “There are three kinds of lies: lies, damned lies, and statistics.” Presidential preference polls are, for better or worse, a form of statistics.
Parsing through the various polls is difficult because few of them give sufficient data to allow meaningful analysis of why they depart from the norm - - and they do depart from the norm; when the range of poll results is as wide as it has been for the past several weeks, with Obama leads ranging from +1 to +14, somebody is wrong, or is using bad techniques, or both.
The most likely explanation for this insane variation is that pollsters are, deliberately or innocently, using poor data collection and processing techniques. It may be coincidental that polls done for MSM publishers and broadcasters have a strong likelihood of being weighted to favor Obama; but then, it may not be all that coincidental..."
Here's a YouTube bit about "Opinion Polls: Getting the Results You Want." (with Nigel Hawthorne, of "The Madness of King George")
And lastly, something from Wizbang entitled: "Odds at Ends - The Pew and Battleground Polls, with a Gallup Chaser" (http://wizbangblog.com/...-a-gallup-chaser.php)
..."I've laid out a pretty harsh accusation against the polls this year, by claiming that all the major polls are far from accurate. The cause of this, in essence, has been that the polls made some key assumptions about turnout, the independents, and the undecided voters. Assumptions which they never tested, and now are finding cannot be trusted. Poll results vary wildly from one another, and not just at different times. The variance for current polls listed at Real Clear Politics for this morning ranges from the Pew poll which advertises a 14-point lead for Obama, to the Battleground poll which says the lead is only 2 points. The variance is too great (and there are polls relatively close to both ends, demonstrating proof of statistical invalidity for the published confidence level) for even the casual observer to accept as a reasonable. There are four polls which show a 10 point lead or greater for Obama, and another five which show a 6 point lead or less. It is mathematically impossible for so many polls to be valid, yet disagree to such a degree with valid methodology. I said this when McCain was ahead, again when Obama climbed in front, and I am repeating it yet again. The starting point to discussing the polls this year, is understanding that the methodology in common use is flawed, and is producing results which cannot be depended upon..."