So, Yahoo! News now has an article titled "Bush Raps Kerry, Slips in Polls." It's based on a recent survey by Newsweek. Unfortunately, this story is a perfect example of why you should treat all media reporting on polls with skepticism. As Powerline notes:
"Newsweek's most recent poll included 345 Republicans, 364 Democrats and 278 independents. This compares to Newsweek's published data for their most recent prior poll, which showed President Bush with a comfortable lead: 391 Republicans, 300 Democrats and 270 independents. Yes, if you drop 46 Republicans and add 64 Democrats, you will get considerably better results for the Democratic nominee." (Hat Tip: The Pink Flamingo Bar & Grill)
The stuff above is called "screening" or weighting" the sample, and it's just one example of polling methodologies you ought to be wary of. Jay Caruso has more on this particular poll.
Other current polls don't seem to square with Newsweek's latest, just as other polls didn't square with Gallup's accounts of a 13% Bush lead a couple weeks ago. Usually, this is just sloppiness rather than bias - but these sorts of gambits can and will be used deliberately by either side.
If polls matter to you, therefore, get used to asking for internals, questioning the questions, and comparing different polls. Caveat elector.
[Update by A.L.: If this subject interests you, you should be reading Mark Blumenthal's 'Mystery Pollster' blog, (via Kaus). Specifically this post...]
See also this post-debate Gallup poll, which also gets into finer detail like trust on specific issues, likability, believability, though enough for the job, etc. in the wake of the debate.
Can you spot any flaws in their method? How do these results compare to the Newsweek poll? The Rasmussen poll? What does this suggest - if anything?
Then add this question to remember and consider later... how will they compare to the Zogby and FOX polls (which have a better record re: consistent sampling, taking the time, and also predictive accuracy)?
Here's a link to a good analysis of polling, Registered Voters (RV's), Likely Voters (LV), and history.
Link here
The real takeaway here is the following results for 2000:
2000: RVs, +1D; LVs, +2R; actual result, +.5D
This means a .5 plus for democrats in party identification in the actual 2000 election .
So the actual results, 2000:
50.25 Democrat,
49.75 Republican.
The percents in THIS Newsweek poll, are:
345/709 = 48.67 Republican.
364/709 = 51.33 Democrat.
The party ID of the newest Newsweek poll tracks much closer to actual party ID turnout in 2000, than the older newsweek poll, which is:
391/691 = 56.58 Republican
300/691 = 43.41 Democrat
So this newer poll, seem to reflect party identification more CORRRECTLY than the last Newsweek poll. The partyID difference in the newest poll from 2000 actuals is 1% for Democrats, a little less than 1% for Republicans, while the older polls difference from 2000 actuals is around 6.75 off, for both Republicans and Democrats. If this is correct, then this particular poll is actually more accurate than Newsweek's last.
This doesn't even get into Independents of course...
What I read for poll information from a republican side is Real Clear Politics
From the democratic side, Ruy Texeira
and MYDD.
I'm sure there are more good Republican sites as well.
Leftists addressed the Gallup poll with the same criticism, assuming that pollsters "weigh" results by party affiliation. Gallup certainly doesn't, and I am quite convinced that the same is true with this Newsweek poll.
When people answer that they will vote for Kerry, they are more likely to consider themselves democrats than last week, when some of the same people wanted to vote for Bush. Many people switch party allegiance as they switch candidate.
I strongly recommend the last post-debate Gallup poll
It supports my view that while most people seem to agree that Kerry “won” the debate, but Bush emerged from his “defeat” considered by the majority of the people who saw the debate to be more believable, more likable and tough enough for the job.
I think that George W. Bush won the debate, if by winning we mean that he got closer to re-election; symmetrically, I believe Kerry lost because he didn’t get any closer to victory on November 2, far from it.
If you want to see the argument in full...
Thanks for the Hat Tip.
I cannot wait for this election to be done. This is such a waste of valuable time. Had there been a candidate with a position like say Howard Dean it would have been a worthwhile experience to clear the air between the far left and the rest of the world. But lurch aint worth it.
Pierre Legrand