So What’s Wrong with Research 2000’s Polling?
After the elections in 2008, Daily Kos, the largest liberal community blog out there, contracted pollster Research 2000 to conduct a large number of race-specific and “State of the Nation” polls. The results of Research 2000’s surveys have come under increasingly intense fire lately, and on July 1, Daily Kos founder Markos Moulitsas Zúniga filed suit against Research 2000 and its owner and CEO Del Ali. As a poll compilator who has used Research 2000’s polls in my projections, I am keenly interested in the beef that the uber-leftist Kos has with them.
Polling is an inexact science, and the numbers that polling firms produce are constantly scrutinized by political observers of all ideological stripes. Sometimes, when results seem out of line with others — or they don’t match one’s preferred outcomes — pollsters can be accused of driving a political agenda. But rarely, if ever, do you hear of a lawsuit brought against a pollster for outright fabrication. Simply oversampling one demographic or another, or asking respondents leading questions, is no grounds for legal action. Moulitsas must have seen something much more significant — and damaging — in Research 2000’s work than just methodological discrepancies
In fact, what he alleges is quite serious, indeed. The lawsuit states that Moulitsas “was approached by a number of independent statistical analysts with regards to Research 2000’s polling for Daily Kos. Their analysis of the published data revealed a number of statistical anomalies regarding the results which revealed that Research 2000 had almost certainly falsified the results in whole or in part.” As Greg Sargent of the Washington Post affirms, “this is a big, big deal. Research 2000 polls have been widely cited by many news organizations, and have helped shape the national political conversation.”
So what exactly left Kos feeling defrauded by Ali and Research 2000? Sifting through the lawsuit itself and comments made by others on both the right and the left of the political spectrum, I’ve identified three main factors which I believe drove him to sue.
Pollster-introduced error
Nate Silver, founder of fivethirtyeight.com, is partly to blame for the disillusion with Research 2000. He recently revised his extensive analysis of pollster performance and published the updated results. Using a massive database of thousands of polls from hundreds of polling firms and numerous weighted metrics, Silver constructed a quantitative method for ranking poll-taking skill. The end of all this number crunching is a value he dubs “pollster-introduced error.” Essentially, the lower that number, the better the polling firm.
At the top of the list of 64 firms with at least 10 polls published during the sample period were such familiar names as The Field Poll and SurveyUSA. At the bottom? You guessed it. Research 2000’s pollster-introduced error was one of the five highest. In fact, no other polling firm releasing as many polls fared worse. Undoubtedly, when Kos saw the polls tied to his website falling so far down the accuracy scale, he must have felt he was not getting his money’s worth. Yet Silver’s calculations, while certainly disconcerting, were just the beginning of the rift between Daily Kos and Research 2000.
But I thought the Daily Kos was a fabrication site. Everything but polls going forward.
Goof! Can’t we trade places and let me be the first saying that Daily Kos is anyway a fiction funded by Soros and mostly surviving by the “useful idiots” unwavering commitment to fraud and grandstanding?
Consider my offer –
Regards -
Hold the raw data until trial then dump it on the court to whipe aout the councel for the opposition.
“Alas, Research 2000 seems reluctant to produce any raw data.”
Their reluctance reminds me of the scientists who will not produce the datasets and methods they used for their global warming research.
“You can’t cheat an honest man. He has to have larceny in his heart in the first place.”
Markos went with the shoddy polling because it reinforced his existing biases.
Well that’s one way to get out of paying the bill. Did Sissy Boy tell R-2000 to run a deficit, it’s the latest thing. Maybe R-2000 can prevail on ACORN to go collect the money due them, you know thug to thug.
That’s what happens when a Liberal trust a Liberal. The conservatives are lied about and the Liberals don’t go back and change the lies, even if they are proven.
The problem with “holding it”, Avitar, is more and more irreversible damage to Research 2000′s business rep is occurring every day the problem stays on the front page. Logic [and here I'm not claiming there is any in all of this] favors a quick resolution, all the way around. That it hasn’t occurred yet speaks volumes as to Kos’s position.
Does anyone know if the Daily Kos used this firm to pump up Senator Bayh’s numbers? The Daily Kos produced a poll that the Senator would beat anyone from the other side by a substantial margin but then Senator Bayh announced he wasn’t running. Maybe the Senator did his own poll?
Wiki on Del Ali @ Research 2000 (as two minutes ago)- the last phrase is ALL CAPS by me:
[...] Del Ali is considered by some to be one of the leading analysts on the political landscape. Since 1986, Del has analyzed over 1500 political races for media as well as for advocacy organizations and businesses. Del appears frequently on programs such as Fox-Television in Washington D.C., National Public Radio, WMAL Radio in Washington D.C. and CNN’S “Inside Politics”. Del is presently the on-air analyst for KPAN radio in Portland. In addition, Del is frequently quoted in The Washington Post, The New York Times, The Christian Science Monitor, and in USA Today. You can find out more about Del by visiting his Op-Ed Page and reading some of his published articles.
His company, Research 2000, is currently being sued for fraud by Daily Kos FOR ALLEGEDLY FABRICATING RESEARCH. [...]
The bio on Wiki is direct from the R2K website, thus it smells.
R2K’s website looks like a kid set it up. The business was registered in Maryland in 2005- convenient for ‘06 mid-terms and ‘08 pResidential elections- for whom and where was Del supposedly ‘polling’ since 1986? The registered owner of R2K is one Paul Rossi, not Del Ali as is purported on the website. The R2K list of ‘clients’ are mainly small media outlets in swing states.
Mmmmm, mmmmmm, mmmmm.
I love the smell of RICO in the morning! Can’t help but wonder if Markos is trying to saving his own Soros funded hide by blowing the whistle on the inconvenient pollster?
Oh, and the ‘more about Del’ op-ed page link? No data. Del Ali sounds just as bogus as his poll results.
Another foolish thought –
Is this Del Ali/ Daily Kos affair just an accident in the otherwise immaculate ascent and reign of dba Obama?
Or it is another sign, that the dba Obama’s superb ascent was just a well planned, well executed Potemkiniade, elements ranging from designed biography, mysterious life-track, mystifying funding, corrupt judicial response, media carpet bombing, academia sycophancy to… fraudulent polls?
And now, for some reasons, the operatives of this Potemkiniade are turning one against another – like Markos against his pal Del?
Heck – besides the vision of some rats plunging in the sea from the deck of a sinking ship, this affair reminds me of Hitler getting Roehm, Stalin finishing Trotsky, or the current fights for turf in Mexico (amonst so many other shows of lefties getting lefties) -
A suivre -
Sometimes when you see a turtle sitting on a fencepost you have to wonder how it got there.
You got it, alceste. In the immortal words of the Not-so-reverand Jeremiah Wright, “the chickens are coming home to roost.”
Obama’s scam had a good run, but it was never going to withstand the scrutiny that it fostered. In the long run, you can’t fool ALL of the people All of the time. Obama was hoping that his long con would last past November, but it looks as if even Obama himself won’t last 4 years.
The one thing the Left does superbly, is to eat its own.
What? There’s no honor among these thieves? I’m shocked!
I’m shocked, shocked to find that gambling is going on in here!
Major Strasser has been shot. Round up the usual suspects.
There’s no honor among LIBERAL thieves who then, in a genteel manner, proceed with a lawsuit. Conservative thieves simply blow each other’s heads off & that’s that.
Now hold on!
There are several statistically valid methods of obtaining the even/odd anomaly. Here is one:
Start with a randomized list of randomly selected people. Divide up the list among several employees. Require each employee to meet some quota of valid contacts. Declare a contact as not valid if the contact does not divulge gender. Make the quota a nice round number like, 40 or 60. Maybe use whole sheets of paper with 14 contacts per sheet and require full sheets. Using this procedure you will ALWAYS end up with an even number of contacts and therefore with the male and female subsamples as both even or both odd.
Incompetence trumps conspiracy as an explanation. At this point I would favor the incompetence of the critic over a conspiracy to defraud.
“Using this procedure you will ALWAYS end up with an even number of contacts and therefore with the male and female subsamples as both even or both odd.”
Why even subsets of male and female respondents some days, and odd other days, if they’re following these stringent procedures you’re suggesting. More likely that they massaged the sets. That’s the point.
Grab an EVEN number of coins from your pocket. Shake them in your hands. Drop them on your desk. If the number of heads is even, the number of tails will be even. If the number of heads is odd, the number of tails will be odd.
Yet this simple phenomena is supposed to indicate bogus data?
What a farce. DailyKos, with their notable penchant for sheer bull represented as fact is suing someone for producing sheer bull represented as fact?
The irony is wonderful.
What exactly caused Markos to scrutinize R2K? Was he ticked off at some results?
54.3% of all statistics are made up on the spot.
The rest are made up by Research2000!
KOS polls always had Obama at 56 percent- love him.
The other 44 percent of us unwashed masses were redneck,
gun toting, pickup driving,
snake handling religious nuts that despised snake oil salesman Obama.
Blasphemy will be rewarded.
Make that 43%. I’m totally up for the redneck, gun-toting, pickup driving & despise Obama part, but I’d never handle a snake, even for God.
“The other 44 percent of us unwashed masses were redneck, gun toting, pickup driving, snake handling religious nuts that despised snake oil salesman Obama.”
Even some of us ‘snake handling religious nuts’ bought the snake oil. (Not I!)
Shame!
As they say there is lies, damn lies, and statistics
It’s standard practice for many pollsters and market researchers in general to hand over the complete raw dataset to the client. in fact, technically, the client, in this case DailyKos, is usually considered to own the data, since they paid for it. It depends on the contract that Kos had with them though.
“It’s standard practice for many pollsters and market researchers in general to hand over the complete raw dataset to the client. in fact, technically, the client, in this case DailyKos, is usually considered to own the data, since they paid for it.”
Good thing the media like the Washington Post did their job and researched Research 2000/Daily Kos’ methodology vs. just accepting their results cart blanche. /sarc
Markos has not paid the bill.
You really don’t enjoy rights on services you haven’t paid for
Kos also is under an oral agreement. Worthless!!!
Gee, a Liberal Dem who thinks he doesn’t have to pay for “stuff”…who’d have guessed?
Time to recall the remarks Kos passed when three American contractors were killed by religion of peace types in Iraq and their burnt bodies hung from a bridge, “F— them”, is how it began. The tragedy to their families, the bestiality of their murderers, didn’t trouble Kos a bit. And he gets guest spots on TV, Democrats appearing on his site, yes, liberalism at it’s finest, the real face of this vicious disease. You think this thing worries about paying bills?
Well at least his wife left him for what is presumably a man, in any case she’s pregnant by it even if it is a liberal.
How are the odds of the subset of men and of woman both being odd or even so far fetched? This is identical to saying that the total number of respondants is`always even.
If the total number of respodants is even, and the subset of mem is even, then the subset of women must be even as well. Likewise, if the total is even, and the subset of men is odd, then the subset of women must be odd as well.
There could easily be a sysmatic reson that they always have (or seek) an even number of respondants.
“If the total number of respodants is even, and the subset of mem is even, then the subset of women must be even as well. Likewise, if the total is even, and the subset of men is odd, then the subset of women must be odd as well.”
But rolling dice, you’d have overall respondents even and odd about the same number of times, given 778 rolls. Every time the number of overall respondents was odd (should be roughly half the time), then the number of men and women in the subset must be odd and even, or even and odd – roughly half the time. Instead they were both odd and both even, something like 776 out of 778 times – and THAT is what defies all odds.
Make sense? That piece cannot be explained away as random.
10 to the 228th, what’s the beef? Do not so very many, accept evolutionary theory in its many variants—but with far worse statistical odds to their side?
Great point!
Please let me know if this is correct, this Markos still used this data as proof in the book that is due to be released so when it is read by those that do not pay attention will find those statistics to be facts?
Polling: The not so fine art of making the numbers say whatever floats the boat of the person willing to pay you to come up with specific results that match your uber partisan position.
Where I come from some folks would say this amounts to creative lying!
In the end, after reading polls for many years I have come to the conclusion that many of them are what is known in the industry as “push polls.” That means the results are tailored to match the results the person paying wants to espouse. If one reviews poll results for previous elections, one would find that few pollsters are actually anywhere near correct. Those who are, are either very good at their work, or they were darn lucky. When you read over some of the questions asked you will be startled to read questions that allow for only one answer & that answer is exactly the answer the person paying wants to hear or be able to spew out as though the results mean something other than on this particular day this particular person felt this way about an issue based on the leading question asked of them.
Listening to many of the political pundits as they tout poll results that support their ideological views which they are selling to anyone who may be viewing or listening in, one gets sick to the stomach. We all know many of the polls, especially the “just before elections” polls, are designed to either rally the base to vote or to try to discourage the opposition’s voters from showing up. Unfortunately, it often works. Some are so gullible they will fall for such antics. I say, vote your conscience & let the chips fall where they may.
Next thing you know, Markos will be sueing ABC for demonstrating what a lame-brain he is by inviting him to join the panel on “This Week”.
He needs to go back and complete Junior High School.
I know I missed it, but what was the subject of the poll in question?