Cameron reached for unscientific "Zogby Internet" survey to contrast with polls showing Dem with "double-digit lead" in MN Senate race
SUMMARY: Reporting on the 2006 Minnesota Senate campaign between Republican Rep. Mark Kennedy and Democrat Amy Klobuchar, Fox News' Carl Cameron falsely compared the results of "recent polls" that "gave Klobuchar a double-digit lead" with "the latest Zogby Internet poll [which] shows Kennedy within seven points." But the "Zogby Internet poll" Cameron cited is not a "scientific" poll of randomly selected participants.
During a report on the 2006 Minnesota Senate campaign between Republican Rep. Mark Kennedy and Democrat Amy Klobuchar, Fox News chief political correspondent Carl Cameron falsely compared the results of "recent polls" that "gave Klobuchar a double-digit lead" with "the latest Zogby Internet poll [which] shows Kennedy within seven points." But the "Zogby Internet poll" Cameron cited is not "scientific": Rather than being randomly selected by the pollster from the general population, poll participants were randomly selected from a group of people who had access to the Internet, knowledge of the opportunity to participate in Zogby polls, and an interest in participating.
The other "recent polls" Cameron noted that show a "double-digit lead" for Klobuchar are "scientific polls" of registered Minnesota voters. A "scientific poll," according to the National Council on Public Polls (NCPP), is one in which "the pollster uses a specific statistical method for picking respondents." For example, the Minneapolis Star-Tribune's July 6-11 poll, which found Klobuchar leading Kennedy 59-42 among likely voters, used "Random Digit Dialing" to reach a sample of "all adults in the state who live in households with landline telephones ...; the sample was not limited to those with listed phone numbers, or newspaper subscribers, or other inappropriate populations."
By contrast, the "Zogby Internet" poll Cameron referred to appears to be a July 24 Zogby Interactive poll conducted for the Wall Street Journal Online. It found Klobuchar leading Kennedy, 49.4 percent to 42.9 percent. According to an explanation of the poll's methodology, rather than drawing from a random sample of likely voters in Minnesota, those selected to receive the survey were drawn from Zogby's list of people who wanted to participate in Zogby Interactive polls:
Online polls were conducted by Zogby Interactive, a unit of Zogby International of Utica, N.Y. Zogby has assembled a database of individuals who have registered to take part in online polls through solicitations on the company's Web site as well as other Web sites that span the political spectrum. Individuals who registered were asked to provide personal information such as home state, age and political party to Zogby, which in turn examined that data and contacted individuals by telephone to confirm that it was valid.
Zogby International telephoned about 2% of respondents who completed the interactive survey to validate their personal data. To solicit participation, Zogby sent emails to individuals who had asked to join its online-polling database, inviting them to complete an interactive poll. Many individuals who have participated in Zogby's telephone surveys also have submitted e-mail addresses so they may take part in online polls.
According to NCPP, in "unscientific polls, the person picks himself to participate."
In an April 26 post on his weblog Mystery Pollster discussing a Zogby survey conducted for the online gambling industry, Democratic pollster Mark Blumenthal highlighted the way in which the methodology for Zogby's Internet-based surveys diverges from that in polls based on a "'scientific' random sample":
Why is it important that the survey was conducted online?
1) This survey is not based on a "scientific" random sample -- The press release posted on the web site of the trade group that paid for the poll makes the claim that it is a "scientific poll" of "likely voters." As we have discussed here previously, we use the term scientific to describe a poll based on a random probability sample, one in which all members of a population (in this case, all likely voters) have an equal or known chance of being selected at random.
In this case only individuals that had previously joined the Zogby panel of potential respondents had that opportunity. As this article [link no longer operative; Google cache link is here] on the Zogby's web site explains, their online samples are selected from "a database of individuals who have registered to take part in online polls through solicitations on the company's Web site, as well as other Web sites that span the political spectrum." In other words, most of the members of the panel saw a banner ad on a web site and volunteered to participate. You can volunteer too -- just use this link.
Zogby claims that "many individuals who have participated in Zogby's telephone surveys also have submitted e-mail addresses so they may take part in online polls." Such recruitment might help make Zogby's panel a bit more representative, but it certainly does not trans[f]orm it into a random sample. Moreover, he tells us nothing about the percentage of such recruits in his panel or the percentage of telephone respondents that typically submit email addresses. Despite Zogby's bluster, this claim does not come close to making his "database" a projective random sample of the U.S. population.
Blumenthal's polling firm, Bennett, Petts and Blumenthal, has conducted polling (subscription required) on the Minnesota Senate race for the Democratic Senatorial Campaign Committee (DSCC). The latest DSCC poll, conducted by Blumenthal's firm from July 16-20, has Klobuchar leading Kennedy 50-34 among likely voters.
From the July 24 edition of Fox News' Special Report with Brit Hume:
CAMERON: While some recent polls gave Klobuchar a double-digit lead in this historically Democratic-leaning state, the latest Zogby Internet poll shows Kennedy within seven points. He's better funded, better known, and is the aggressor, trying to put Klobuchar on defense on security matters, particularly the war in Iraq.
to worry about polls, anyway. Diebold is on their side.
No Diebold voting machines here, or any voting machines as far as I know.
let them think they're close. then they won't try so hard to disenfranchise voters and put two machines in a precinct for a thousand voters.
Every poll I had heard of about this race put Amy Klobuchar ahead of Mark Kennedy with a double-digit lead. It figures that a scumbag like Carl Cameron would cherry-pick one poll that shows Klobuchar with a seven point lead, which is still a pretty decent lead.
THANK YOU. njguy93@yahoo.com
This hits close to home as the Star Tribune is my hometown paper. The Star Tribunes polling results have been notoriously weak over the years and consistently skewed (incorrectly) in favor of Democrats. This has been documented by conservative interests in the state of Minnesota time and time again. This Excerpt from the Conservative Voice:
"Since 1987, when the Star Tribune hired Rob Daves as their pollster, the final Minnesota Poll results for Republican candidates have on average been 5.2 percent under the actual election results. Since 1998, the final Minnesota Polls have underestimated Republican results by an average of 7.26 percent, while understating Democratic results by only .054 percent. In 1998, the poll predicted that Skip Humphrey would win the gubernatorial election with 35 percent. On Election Day, Skip garnered a whopping 28 percent, enough to put him in a solid third place. The fact is that while the Star Tribune might lie, numbers don’t. Now put yourself in the position of those in charge of this consistently skewed poll. What would you do if your results were so wrong, so predictably well predictable? Perhaps you’d look to your pollster and ask a few questions. Maybe you’d even look for a new pollster. Not the Star Tribune. The inaccuracy of these polls is a direct result of their polling director’s insistence upon under-representing Republican voters in his samples. And their results are consistently contradicted by almost every respected poll. For instance: · The most recent Rasmussen numbers show a dead-heat in Minnesota, with Bush and Kerry both at 46%. · The latest Strategic Vision poll has a statistical dead heat with Kerry at 47% and Bush at 46%. · Thursday’s MPR/Pioneer Press/Mason-Dixon shows Bush leading Kerry 46% to 44%. · Thursday’s USA Today/CNN/Gallup poll also showed the race in Minnesota tied at 45%. The Star Tribune, like John Kerry himself, is quite simply out of the mainstream. The paper has responded to these claims by trying desperately to defend their methodology while simultaneously lashing out at the Republican Party, deeming any criticism of polling director Rob Daves "shameful and misdirected." Fine. But if the Star Tribune Minnesota Poll is so accurate; if Mr. Daves is such a fine pollster; and if the Star Tribune has favored accuracy over politics; then why isn’t Fritz Mondale our Senator? Why wasn’t Skip Humphrey our Governor? Why didn’t Al Gore win this state in a landslide? They predicted all of the above. Currently, every major national poll shows President Bush with a growing lead over John Kerry and major polls in Minnesota almost invariably show a dead heat. Meanwhile, the Star Tribune insists that Kerry has somehow built a virtual double-digit lead. Someone has to be right. "
Note: Kerry did win Minnesota but by a much slimmer margin than the 9% lead the Star Tribune gave him. I'm not saying the Zogby poll is accurate either, but for goodness sakes don't bet your rent money on the Star Tribune. You've been warned.
Heres the link to the article:[link to www.theconservativevoice.com]
One last article on the Star Tribs polling problems (written by Scott Johnson, the Powerline guy, not the one from around here). [link to www.claremont.org]
For the record, the Star Tribune's final poll (subscription required) of the 2004 presidential election (10/31-11/1, 2004) had Kerry at 47 percent, Bush at 43 percent, "Other" at 2 percent, with 8 percent "unsure." Margin of Error was +/- 3.7 percent.
That would be a 4 percent margin.
The MN final results are perfectly compatible with the those results:
I would welcome you to track the Star Tribs results in November. If they run true to historical form, the Repubs will outperform the Star Tribs polling numbers. As you showed they did get the 2004 presidential race correct in the end, so they get due credit for that. They missed many others before that, all in the same direction surprisingly.
but I take them all with a grain of salt, whether I like the results or not.
Most groups pick the poll with the numbers they like best, some just do it more dishonestly (using unscientific ones, for example)
One point about the internet polls; it's usually cited that these exclude lower income people, and that skews conservative. I don't know how true that is, but I personally think an equally important factor is time. Yeah, I burn some time on MMFA and some other places when I should be doing other things, but learning and arguing are two of my favorite things.I don't consider it wasted time, even at my lowest name-calling, snide remark worst, it's good times.
Taking a poll, on the other hand, seeems very menial to me most of the time.
I do know co-workers who take polls regularly online, and they're all rightys.
I think clicking on "yes" or "no" is sort of a low-impact workout for people who like simple black/white arguments, consequently conservatives are more likely to go through with polls.
Don't forget-this also explains why cons vote like crazy. IMO, our elections are skewed right, but theres nobody to blame but the thinking people who don't vote.
"trying to put Klobuchar on defense on security matters, particularly the war in Iraq."
I am curious how the war in Iraq is making the U.S. more secure? I'll bet the voters would like to know as well since over 60% are against the war there.
These people really do live in a fantasy world.
More lies to follow.
In my communication theory research class and in my statistics classs (both required for journalism students), sampling is one of the main things that is covered. The sample needs to be random. If you just get a bunch of volunteers to take the poll there will be bias. I guess the fact checkers at Fox were too busy hiding the massive erections they had after seeing a poll in a republicans favor instead of actually checking. Either that or they didn't go to school, I guess they are looking out for the ignorant people they produce their programs for...
The Carl Cameron reporting of the Zogby poll was an ignoramus reinforcing a fraud. Any student of statistics would be brought to tears. It was bad enough when the non-response factor in using land line phones for sampling became indefensible – years ago. Ask yourself, would you answer a land line phone (your cell phone isn’t even in the running) to give 20+ minutes of your time to XYZ Polling Company – which is probably a neocon operation which is probably using push poll questions? Who would? If this is over your head, take a course in basic statistics. Putting that little plus or minus 3% in the corner doesn’t make it scientific. It’s a fraud. Its only possible and limited value would be to track trends in the same non-random sample – chosen in the same fraudulent non-random way. Don’t ask the polling companies about this (and I worked for Gallup); ask the ethical statisticians.
I live in MN and volunteered for the Klobuchar campaign. It is "generally believed" (+/- levels of ennui) that regardless of his Republican affiliation, Mark Kennedy is an idiot and will not win the Senate seat.
"Generally believed" by whom? The Uptown crowd? I wasn't aware of it. I think Amy will probably win as well for other reasons but I hadn't heard the "Kennedy is an idiot" theory. I've heard him speak and he didn't come across that way to me.