Pollster.com

Articles and Analysis

 

POLL: Zogby National '08 Match-ups


A new Zogby Interactive online survey** (story, results) of 9,150 likely voters (conducted 11/21 through 11/26) finds:

National General Election Match-ups:

    Huckabee 44%, Clinton 39%
    Thompson 44%, Clinton 40%
    McCain 42%, Clinton 38%
    Giuliani 43%, Clinton 40%
    Romney 43%, Clinton 40%

    Obama 47%, Thompson 40%
    Obama 45%, McCain 38%
    Obama 46%, Huckabee 40%
    Obama 46%, Romney 40%
    Obama 46%, Giuliani 41%

    Edwards 45%, Thompson 42%
    Edwards 44%, Romney 42%
    Edwards 44%, Giuliani 43%
    Edwards 43%, Huckabee 42%
    Edwards 42%, McCain 42%

** Note: This survey used a non-probability sample. Respondants had previously volunteered to be interviewed online.

 

Comments
Andrew:

Due to Zogby Interactive's inaccurate past, we should not trust this poll too much.

____________________

dcs:

Does Pollster.com consider this Zogby do-it-yourself poll to be scientific enough to dignify by posting its results on your usually rigorous site?

We come here for information that might give us some clue about the dynamics of this campaign, which this poll does not even come close doing.

Finally, the results of this "poll" speak for themselves. Do you really believe that Clinton is losing even to a GOP candidate like Huckabee who virtually no one has heard of outside of Iowa? All this poll shows is that the minority of very "passionate" voters, who tend make up the bulk of Clinton's detractors, overwhelmingly responded to this "interactive" poll. Most regular people do not bother taking such "polls" as they rightly consider them a waste of time.

____________________

Internet polls are useless, especially when they come from a source as suspect as Zogby.

____________________

ronbo:

I'm surprised that give any interactive poll - let alone one from the Zog - equal dignity with Gallup, Rasmussen, et al. It's not your fault that the media pick up on these polls and report them as if they actually mean something, but as dcs says (three times!) we expect better from this site.

I don't deny that online research can be valuable qualitatively, but on a quantitative level it's just BS.

____________________

Paul:

Any poll that has all five Republicans (including Huckabee) over Clinton, and at the same time Obama and Edwards over all five Republicans make no sense at any level.

____________________

mikeel:

Z-O-G-B-Y spells O-U-T-L-I-E-R.

Actually, he's pretty close to Rasmussen. No doubt Hillary has slipped, but are all five GOP candiates statistically equal as this poll suggests?

I don't think so.

____________________

The reason we post polls is so you are aware of them. I don't think we are doing anything else here.

Our goal from the start has been to post all the polls, without prejudice either way and certainly without partisan or candidate favoritism.

Do you really want us to start posting only the results we agree with?

As you might notice, we also provide analysis of the polls, and there I don't think we've been at all reluctant to criticize polls we think are out of line. Indeed, I'm often attacked here for calling a poll an "outlier" when the statistical evidence makes it so, but that doesn't fit people's preferences.

I'll in fact be posting an analysis of the Zogby results shortly. Just as we usually do.

Charles

____________________

John Bainbridge:

I was shocked that Reuters reported this poll as straight news and even reported a 'margin of error'!!!??? Margin of error on a non-probability sample is non-sense. There is no meaningful population (or probability space) for such a piece of doo-doo to have a margin of error for!!! I no longer have any respect for John Zogby permitting an incompetent minion to report a margin of error for a self selected "poll"!!

____________________

"Do you really want us to start posting only the results we agree with?"

It's not the results most people are complaining about, it's the methodology.

I did like the analysis. However, I think the answer is a lot simpler. Zogby used a biased sample.

____________________

"Do you really want us to start posting only the results we agree with?"

It's not the results most people are complaining about, it's the methodology.

I did like the analysis. However, I think the answer is a lot simpler. Zogby used a biased sample.

I just got a no suitable nodes error, so I'm going to re-post. If the message comes up twice, it's not my fault.

____________________

AD Lord:

Well, I hope you're all correct, but Zogby's interactive polls have been quite accurate in the past. If you check Zogby's own report of this poll on his Web site, there's a link to an explanation of the technique used. He certainly does try to get a representative sample of the population. And he provides past examples in which his interactive polling has been quite accurate. Of course, his result here is certainly an outlier, but it would be nice to know why instead of just dismissing it out of hand.

____________________

AD Lord:

Well, I hope you're all correct, but Zogby's interactive polls have been quite accurate in the past. If you check Zogby's own report of this poll on his Web site, there's a link to an explanation of the technique used. He certainly does try to get a representative sample of the population. And he provides past examples in which his interactive polling has been quite accurate. Of course, his result here is certainly an outlier, but it would be nice to know why instead of just dismissing it out of hand.

____________________

PlacitasRoy:

"And he provides past examples in which his interactive polling has been quite accurate. " Didn't post examples of the ones that didn't confirm the accuracy did he?

Well that damned old liberal media took the bait and published the results without bothering to mention this POS has no validity at all.

The reporting was worse than the "poll."

____________________



Post a comment




Please be patient while your comment posts - sometimes it takes a minute or two. To check your comment, please wait 60 seconds and click your browser's refresh button. Note that comments with three or more hyperlinks will be held for approval.

MAP - US, AL, AK, AZ, AR, CA, CO, CT, DE, FL, GA, HI, ID, IL, IN, IA, KS, KY, LA, ME, MD, MA, MI, MN, MS, MO, MT, NE, NV, NH, NJ, NM, NY, NC, ND, OH, OK, OR, PA, RI, SC, SD, TN, TX, UT, VT, VA, WA, WV, WI, WY, PR