[Timeout]

"Reporters" questioned his results, so he added more Rats. No doubt he was terribly frustrated that he didn't have enough sauce to push Daschle back into the lead.

[stockpirate]

ZOGBY polls are as worthless as tits on a bull.

[tirednvirginia]

He DID have enough sauce, unfortunately, to put Kerry back in the lead.

While I hope Thune wins, its not the race that has my stomach in knots.

[Timeout]

I went looking for this article because of an article in today's Washington Post:

"There's almost a panic [among Democrats] around the nation about Daschle being able to cling to his seat," Thune campaign manager Dick Wadhams said.

Friday's Question: Not so, Daschle supporters say. For starters, they say, the Zogby poll published in the Rapid City Journal is flawed. It showed Republican Thune leading Daschle, 48.5 percent to 45.5 percent, just within the margin of error. At first, however, the poll had shown an even larger Thune lead, which seemed so improbable that the pollsters adjusted their voter turnout estimates and arrived at the narrower gap.

Democrats scoffed, saying the poll remains suspect. It contradicts other public polls showing Daschle slightly ahead, and it showed House GOP challenger Larry Diedrich leading Rep. Stephanie Herseth (D). Even some Republicans find that hard to believe.

[MEG33]

Zogby adjusts according to his mood..No one knows his methodolgy.

[ClintonBeGone]

Zogby is normally right on in Presidential years. Don't discount his numbers.

[StAnDeliver]

Excellent post. Zogby is not a pollster, but a spinner. The problem with the vast lack of poll comprehension (thank you, public schools) by the body politic is that, in turn, spinners like Zogby can bury the garbage stink sauce in the MOE. After blowing the 2002 Congressional races, Bush's +4% / +290 EV win in 2004 will once and for all fully discredit Zogby and his methods.

[TBBT]

The Horserace Blog's view of Zogby:

Zogby: Drummond seems to think that Zogby simply fell ass-backward into his present notoriety. Zogby predicted 1996 accurately and came close in 2000. However, his track record is generally lousy. Zogby has a devastating methodological problem -- his polls are not conducted randomly. He uses regional quotas. He is the only one of all these polls (that make any methodology known) that employs this technique. Furthermore, Zogby does not conform his data to industry standards. Rather, he uses -- among other sources -- his previous data. Neither of the standard-setters in the polling industry accept this practice. Zogby also weights his polls to strictly conform with the 2000 partisan turnout results -- a result that BC04 has spent tens of millions of dollars to change. Zogby, a supposedly independent pollster, also called the race for Kerry...IN THE SPRING! Zogby is also one of the chief practitioners of the internet poll, which is really quite unacceptable. Because I have (unfortunately) used Zogby here at this site, I will quote the very estimable Drummand at length (consider it part of my pennance): "All in all, Zogby’s habit of confusing his personal opinion with data-driven conclusions, his admitted practice of manipulating the respondent pool and his demographic weights, by standards not accepted anywhere else, along with mixing Internet polls with telephone interview results, forces me to reject his polls as unacceptable; they simply cannot be verified, and I strongly warn the reader that there is no established benchmark for the Zogby reports, even using previous Zogby polls, because he has changed his practices from his own history."

The Horserace Blog's view on other polling outfits can be found here.

[Tarpon]

http://www.aberdeennews.com/mld/aberdeennews/news/10051938.htm

Revving up the dead Indian vote for 'lil Tommy. There is always a way to fix an election if you are clever.

[Aetius]

The bigger question is how it is that so many Bush supporters can also support Daschle, who thwarts Bush at every turn.

If Thune were to beat Daschle, that would earn him a lot of gratitude from the GOP. He would be a hero, thus making it easier for the Junior Senator to bring home some of the bacon that Daschle apparently does (how else could he win in SD???). If SDans realized this then it probably wouldn't even be close.

[ThinkingMan]

I really wonder how accurate any polls are in this state. I live in Sioux Falls and I have not been polled even ONCE during this election. I really wonder who they are calling.

On a side note, I have had a LOT of fun with all the Daschole workers that keep showing up. I just ask what it would take for me to convince them to vote for Thune. They used to engage in dissucussion, lately they just scurry off as fast as they can.

I have a real good feeling about this election!.

[Dr Snide]

Zogby has always admitted this. Acouple of months ago on MSNBC he admitted to changing his national polls to reflect 40% Dem and 32% Republican. His polls are worth less than then ethics training at the Dem National Convention.

[solzhenitsyn]

A poor scientist tinkers with his statistical methods till he gets the results he wants. "If you torture the data, it will confess."

[TBBT]

Here's the real problem with Zogby's polls. If Zogby shows Kerry up by any amount, it will be the Gold Standard in the days media coverage. All other polls showing Bush up will be ignored.

Got to keep the Dem's morale up and Zogby is only to happy to oblige in that effort...

[sweetliberty]

After what happened last time with the 3 county reservation "votes" all coming in when Thune had had a solid lead, many of which exceeded the number of eligible voters in those areas, I have absolutely zero faith in the legitimacy of any election results in South Dakota. The key to elections isn't independent and swing voters and battleground states; it is voter fraud.

[KenmcG414]

Watch the cemetery vote. Daschle is expecting a large turnout of SD's deceased to vote for him.

[M1thumb]

I would like to see a poll where we get the pick the results. Pollsters should list their results along with all the tweaks/assumptions/"sauce" then we can pick the one we like. If you think there are equal R's and D's, pick that; more likely R's than likely D's pick that result, and so on....

It's all garbage anyway, we might as well pick the one we like.

[HoosierFather]

I've been observing Zogby for the past few election cycles. It's become clear that in the lead up to elections he massages the data to create the impression he desires. For example, he may realize from the raw data that Daschle is in trouble. So, he adds his special sauce to exxagerate a 2-3 point Thune lead to 5 points. The message here is for the Dims to start mobilizing their base and the fraud machine on the reservation. For President, contrary to most other trackimg polls, he juices it up for Bush about 2 weeks out, then reverses the trend in the last week to create the impression of momentum for Kerry. But, what I find most disturbing is the he injects himself into these discussions. One day it's Kerry's race to lose, then it's Bush's race to lose. He should (like most reputable pollsters) just report the data and not inject his political spin.

At the end of the day, this is all just statistical sampling and it has it's own inherent variability. By Zogby altering the composition of the likely pool of voters depending on the political situation, he can influence the message, but he sacrifices the accuracy (and hence the reliability) of the data.

I think the best way to look at polling data is to watch the RCP average. The RCP result averages a number of tracking polls (including Zogby). This method increases the number of respondents (because they use a composite of 5-6 polls)and evens out the bias of each independent pollster. If you look at this average, Bush has been bouncing between a 2-3.5 point lead (nationally) in a 3-way race for the past 10 days. In the end this may not be the exact difference in the election, but the RRCP average allows one to clearly observe the trend over time. At the moment, things are ticking slightly for Bush.

[Salvation]

Seemingly titlted!

[OldFriend]

Zogby is the handmaiden of the left.

[truecons]

Zogby Research Indicates Earth Is Flat

 

Shocking the scientific community, at a press conference today political pollster John Zogby presented data he says conclusively shows that the earth is, indeed, flat.

 

"We've known this all along", said Zogby, under fire recently for his questionable polling procedures that some say "cook the books" to produce desired results. "I mean, for crying out loud, look around!"

 

When pressed for details, Zogby presented a chart with numbers on it, leading journalists present to look at each other, give that "I didn't know that but it makes sense" look, and nod approvingly.

 

Zogby then went on to describe their methodology, which involved two rocks and a long string. "We stretched the string between two towers a mile apart and let about 100 feet dangle down. Then we tied a rock to each end of the string. We measured the angles between the horizontal and vertical parts of the string and got 7.16x10-3 degrees from 90, which would indicate that the earth was a circle with a radius of approximately 4000 miles."

 

"Well, we immediately know that was wrong. I mean, that's such a small angle we figured we must have measured wrong. So we corrected based on the exit polling we did during the 2000 election in South Dakota which was 49% Republican and 33% Democrat. We took that ratio, which is 1.48, adjusted it with a correction factor code named "Special Sauce", and came up with exactly 7.16x10-3! Subtracted from our original value, it showed an exact 90 degree angle, consistent with our previous certainty that the earth is, indeed, flat."

 

"I assure you, after about an hour of mutual back-patting, we went out and had one honkin' pizza party...sausage, canadian bacon...the works!"

 

When asked to explain how they even began to pursue this line of research, Zogby gave a surprising answer. "It all began back in 2000 when we were doing our exit polling. We met a wonderful young man who was with the office of Senator Tom Daschle. We got talking over a few beers, and one of our researchers let it slip that he wasn't all that sure about this round earth thing. Then this young man, I think his name was Pfeiffer...you know, like Michelle...wwwrrrooowwww!...he said something that I think will end up changing our view of the world forever. He says, 'You know...no sane person in America believes the Earth is round'."

 

"And the rest is history. Oh, and by the way, our 2000 polling data also proves that Nebraska is actually slightly concave...go figure".

 

 

John Zogby,
demonstrating how his proctologist
found that "correction factor"