Posted on 10/02/2004 9:50:08 PM PDT by dvwjr
The curious part of the partisan internals is that Kerry leads in this latest October 2nd Newsweek/PSRAI poll despite the increasing preference of self-identified Democrats for George Bush. Poll results seem to be due to the increased percentage of self-identified Democrats, with a corresponding drop in the percentage of self-identified Republicans. It will be interesting to compare these internals with other polls conducted in similar time periods.
If the poll result percentages in the table show below are rounded off so as not to have a fractional component, the results should match the published polls for each polling organization. The fractional differences in the table poll results are due to the calculations done to distribute the sample number of Registered voter responses which was necessary to avoid any great inaccuracies due to the rounding already performed by the polling organizations when their results are published.
Source: Newsweek poll, September 30 - October 2, 2004
Source: Newsweek poll, September 9-10, 2004
Source: Newsweek poll, September 2-3, 2004
Source: Newsweek poll, July 29-30, 2004
Source: Newsweek poll, July 8-9, 2004
Source: Newsweek poll, May 13-14, 2004
Source: Newsweek poll, March 18-19, 2004
I have created a temporary 'ping' list to many who had expressed interest in these 'Rep/Dem/Ind' poll breakdowns. If you wish to be added (or removed) from this 'ping' list, please place a reply on this thread and I will attempt to clean-up this list so as to not bother those who do not wish to read this type of poll analysis.
Hope this helps...
dvwjr
Poll ping...
dvwjr
Thanks for the ping.
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.
http://story.news.yahoo.com/news?tmpl=story&cid=514&e=2&u=/ap/20041003/ap_on_el_pr/bush
http://www.papadoc.net/PinkFlamingoBar.html
http://jaycost.blogspot.com/2004/10/problems-with-102-newsweek-poll.html
http://smythesworld.blogspot.com/2004/09/another-wacky-poll-from-gallup-this.html
Leftist propagandists looking to sap the morale of real Americans.
Pathetic in the age of the internet that they are still trying to pull this same scam.
Look at the makeup of Republicans vs. Democrats in Newsweek’s poll from September 11, 2004: NEWSWEEK POLL: Campaign 2004.
391 Republicans (plus or minus 6) 300 Democrats (plus or minus 7) 270 Independents (plus or minus 7)
Compare against the same data from the new poll, which Newsweek is using to claim that Bush’s poll lead has “evaporated:” NEWSWEEK POLL: First Presidential Debate.
345 Republicans (plus or minus 6) 364 Democrats (plus or minus 6) 278 Independents (plus or minus 7)
Did Newsweek choose a lower percentage of Republicans for the first debate to set up Kerry’s “comeback,” or did they stack the deck with more Democrats in the second poll?
(Hat tips to all who emailed about this.)
UPDATE at 10/2/04 6:54:49 pm:
The loons at Daily “Screw Them” Kos are watching this topic: LGFers moan about Newsweek poll.
does your chart take into account Newsweek's weighting of the poll? They don't weight by party, but they do weight by subgroups... which results in more Democrats.
I believe it was 39 to 34 with the weighting.
I love you.
You know, in a totally platonic guy kinda way.
I KNEW Newsweek was manipulating their polls.
Yep. Bunch of people posted this a few hours ago. Newsweak/Princeton is either playing games, or Kerry made a lot of people identify themselves as Democrats from Republicans.
Let's see what Gallup does, especially in light of that ad by Moveon.org in NY Times.
Thanks for posting this, I just have a quick question. You said, "The curious part of the partisan internals is that Kerry leads in this latest October 2nd Newsweek/PSRAI poll despite the increasing preference of self-identified Democrats for George Bush.." Correct me if I'm wrong, but those results, which you attribute to the greater number of self-identified Democrats are not 'corrected' by the re-weighting of the sample that you have done, the totals running down the right side of the chart. Is it possible for you to re-weight that portion also? I don't know if that would show more than 12% of the democrats now supporting Bush. Just wondering....
I'm no statistician, but if Kerry won the debate so convincingly and the sample for the poll included such a shift in the numbers of Republicans and Democrats from the prior poll, should Kerry be WAY up? My point is, it can't be both, can it? If Kerry won the debate and gained enough votes to wipe out Bush's lead, that should be something that would be reflected in the same kind of sampling as the prior polls. Instead you have a huge shift in sampling to where there is now a much larger percentage of democrats in the poll. So unless the debate caused an enormous change in party identification, which of course is ridiculous, then it would seem like if you normalized the numbers (just for comparison) to reflect what the prior sampling percentages of Republicans to Democrats were, then Bush would still be way ahead. Am I missing something?
Jay Cost's blog had another interesting tidbit they discovered in the poll's internals:
#3. It is not problematic to me that it is 52% women and 48% men. What I find problematic is that the *men* who were surveyed support Kerry 47% to 45%. Not even Bob Dole did this poorly in 1996. This indicates that they undersampled Republican men. This would, incidentally, make sense in light of the fact that almost all of the sample was done on Friday. What are large swaths of Republican men doing on Friday nights in those red states in the fall? A. During the day they are working; B. During the evening they are at HIGH SCHOOL FOOTBALL GAMES!
Here's the link to that blog. He's got a great point.
Geez, I guess I should have included the link like I said I was going to do: http://jaycost.blogspot.com/2004/10/problems-with-102-newsweek-poll.html
Thank you. I'm not sure I understand this, but I figure if I keep looking at them, sooner or later I'll figure it out :o)
I am not sure this shows anything at all.
Look, when each party's voters are overwhelmingly favoring their own candidate, clearly a sample with more Dems than GOP are going to increase Kerry's result. But what does that really mean? The random phone calls were made. More people sampled this time versus before said they were Dems. They got recorded. Kerry is reported in the lead.
So the question arises, why does the total of Dems vs GOP in a sample vary so? Note that these are not targetted phone calls. The respondents self identify on the phone. How is it that so many more of one party vs the other are encountered by the phone calls -- and that disproportion can change so much? This many people didn't change party affiliation in 3-4 wks. This is all supposed to be about trends. How can there be a trend perceived when such a variance in who answers the phone is encountered.
I am afraid I do have an answer and it has NOTHING to do with the debate. This is the time frame when the new Dem registrations will be taking place. If they have truly out registered us, then they exist in greater proportions in the samples this month versus last month and we're in trouble.
But if not that . . . then it may be that the only way we can get any decent data on trends is to look strictly at the variance in independents' preferences.
please add me to your list.
Have you emailed this to Newsweek, the poll company, Hugh Hewitt, CBS, etc. to get this data out there? This looks like another rathergate Jr. in the making! :p Just kidding about that, but Newsweek should be informed of the sample irregularities.
Newsweek Poll
First Presidential Debate
Princeton Survey Research Associates International
Final Topline Results
(10/2/04)
N = 1,013 Registered Voters
Margin of error: plus or minus 4
Interviewing dates: September 30-October 2, 2004 (interviewing on 9/30
limited to the Pacific and Mountain time zones after the presidential
debate concluded)
SAMPLE SIZE/MARGIN OF ERROR FOR TOTAL ADULTS:
1,144 Total adults (plus or minus 3)
SAMPLE SIZE/MARGIN OF ERROR FOR REGISTERED VOTERS SUBGROUPS:
1,013 Total Registered voters (plus or minus 4)
481 Men (plus or minus 5)
532 Women (plus or minus 5)
345 Republicans (plus or minus 6)
364 Democrats (plus or minus 6)
278 Independents (plus or minus 7)
SAMPLE SIZE/MARGIN OF ERROR FOR DEBATE VIEWERS SUBGROUPS:
770 Debate viewers (those who say they watched at least some of the
debate) (plus or minus 4.1)
369 Men (plus or minus 6)
401 Women (plus or minus 6)
265 Republicans (plus or minus 7)
274 Democrats (plus or minus 7)
215 Independents (plus or minus 8)
NOTE: Data ares weighted so that sample demographics match Census Current
Population Survey parameters for gender, age, education, race and region.
Ssample sizes listed above are unweighted and should NOT be used to compute
percentages.
So here would be the Newsweek raw, Newsweek raw (plus missing 'other) and my calculations from their published R/D/I splits in question 1a/1b. I think that this is what you are asking about...
Hope this helps...
dvwjr
Hope this helps...
dvwjr
Disclaimer: Opinions posted on Free Republic are those of the individual posters and do not necessarily represent the opinion of Free Republic or its management. All materials posted herein are protected by copyright law and the exemption for fair use of copyrighted works.