Nate Silver accuses pollster of possible fraud

[grantcart]

http://www.fivethirtyeight.com/2009/09/strategic-vision-polls-exhibit-unusual.html


Yesterday, I posed several pointed questions to David E. Johnson, the founder of Strategic Vision, LLC, an Atlanta-based PR firm which also occasionally releases political polls. One of the questions, in light of Strategic Vision LLC's repeated failure to disclose even basic details about its polling methodology, is whether the firm is in fact conducting polling at all, or rather, is creating fake but plausible-looking results in order to increase traffic and attention to its core business as a PR and literary firm.

I posed that question largely as a hypothetical yesterday. But today, I pose it much more literally. Certain statistical properties of the results reported by Strategic Vision, LLC suggest, perhaps strongly, the possibility of fraud, although they certainly do not prove it and further investigation will be required.

The specific evidence in question is as follows. I looked at all polling results reported by Strategic Vision LLC since the beginning of 2005; results from 2008 onward are available at their website; other polls were recovered through archive.org. This is a lot of data -- well over 100 polls, each of which asked an average of about 15-20 questions.

. . . .

I haven't really seen anyone approach polling data like this before, and I certainly haven't done so myself. So, we cannot rule out the possibility that there is some mathematical rationale for this that I haven't thought of. But it looks really, really bad. There is a substantial possibility -- far from a certainty -- that much of Strategic Vision's polling over the past several years has been forged.

I recognize the gravity of this claim. I've accused pollsters -- deservedly I think in most cases -- of all and sundry types of incompetence and bias. But that is all garden-variety stuff, as compared against the possibility that a prominent polling firm is making up numbers whole cloth.

I would emphasize, however, that at this stage, all of this represents circumstantial evidence. We are discussing a possibility. If we're keeping score, it's a possibility that I would never have thought to look into if Strategic Vision had been more professional about their disclosure standards. And if we're being frank, it's a possibility that might actually be a probability. But it's only that. A possibility. An hypothesis -- as yet unproven

[cliffordu]

1. Wow. This could be significant.....

and not isolated......

[grantcart]

3. actually I think Nate is saying that it is isolated.

His logic is that the final digits do not appear to be random and that there is evidence that when people make up numbers they will not pick numbers at random but continue to hit on numbers they think are random.

This and an absence of answers to other questions led Nate to accuse them of possibly just plain making numbers up. Othe pollsters may be accused of bias but here he is suggesting that they just made the numbers up.

[cliffordu]

8. I know I make numbers up all the time.....

[bertman]

12. clifford, I know this will probably cause your snarky head to blow clean up, but I

have to thank you for the A number 1 snark you conjure up post after post. You are truly the SnarkMaster.

B-)

[cliffordu]

13. You forgot your sarcasm tag.

:rofl:

[bertman]

17. Oh shit. You're right.

[grantcart]

19. oh god, now you have done it.

The last time Cliffordu learned he had a fan he couldn't sleep for 3 nights.

[Puzzler]

16. If you check the comments section...

... it appears that some (maybe almost all) of the other offices are just PO boxes. Is this even a real organization of any size? Or just a few people making stuff up?

[Jackpine Radical]

22. What's the big deal?

My research indicates that 83% of all statistics are made up on the spot anyway.

[myrna minx]

2. Wow. K&R n/t

[autorank]

4. Good for him k*r

And I'm glad that someone prominent in the polling game is just saying this - this is so lousy,
it looks made up. Failing to provide detail is one way to secure your track. If they're making it
up, providing descriptive data and cross tabs would be difficult since there would be obvious
inconsistencies. Too much secretiveness in polling.

[grantcart]

5. SV has announced that they are hiring lawyers lol

[autorank]

7. LOL is right

They need to keep saying that since they're the only party to initiate action and that gives
them control of the action. This is a big limb and Silver is out there. I suspect he's got
his ducks lined up. I've actually disagreed with him in print on one analysis, his treatment
of the initial election fraud data out of Iran. In that instance, he qualified his analysis
and said someone from the region (South Asia) should know more. In general, his work is quite
meticulous, particularly on the MN recount -- didn't he call it just about exactly? Very helpful
stuff.

[Me.]

20. I'm Instigating A Lawsuit Against You

I have as much chance of succeeding as they do

[autorank]

25. You'll be hearing from my law firm

Dewey, Cheatum, & Howe

[grantcart]

6. kick

[Hekate]

9. Wow. KnR. nt

[blogslut]

10. Kick

Go get em' Nate.

I'm looking backwards @ SV LLC and finding a rather interesting business connection in their past. Shhh.... ;)

[alfredo]

11. Let us know as soon as you nail down the info.

[grantcart]

14. and what did you find?

[blogslut]

15. Not sure I want to say in public

It's the kind of info that can be disappeared fairly easily.

[Jackpine Radical]

23. Now, THIS is the old DU I remember from times past,

when an somebody would find an interesting string and start pulling on it, and then others would join in with their research contributions, and pretty soon they had the whole thing unravelled and laid bare.

[Emit]

18. Johnson "Keep counting till you win election"

Gregoire's "election under such dubious circumstances reinforces the belief of many Americans that Democrats will do anything to win an election -- even steal it."

Keep counting till you win election

By DAVID E. JOHNSON
GUEST COLUMNIST

If you don't win the election on the first count -- demand a recount and litigate until you get the result you want (or the U.S. Supreme Court says enough of this foolishness).

That has become the Democrats new mantra as seen in the past week's certification of Christine Gregoire as governor of Washington following three counts of the ballot; two of which she lost.

~snip~

Gregoire may well be sworn in as the next governor of Washington, but at a very high price -- not for herself but for the Democratic Party. Her election under such dubious circumstances reinforces the belief of many Americans that Democrats will do anything to win an election -- even steal it.

For a political party already suffering from the perception that it is out of touch with American values, this new perception could be deadly. Most Americans fear that lawsuits over election results will become the norm in national politics and want this stopped -- indeed the Washington theft reinforces the idea.

If Democrats are perceived as the cause for these lawsuits, could further electoral punishment be in their future? In 2006, if they lose more Senate seats and governorships, they might begin to get the message, or, perhaps, they might sue voters. In 2008 they could then nominate Gregoire with the slogan "If at first you don't win, try, try, try again until you get the result you want."

http://www.seattlepi.com/opinion/206360_gov04.html

More about Johnson:

BIOGRAPHY

As CEO of Strategic Vision, LLC, a leading public relations and public affairs agency, Mr. Johnson is recognized as a leading republican pollster and strategist. Johnson's political career began when he worked on Bob Dole's Presidential Campaign in 1988 after graduating from Florida State University in Political Science. Since then, he has overseen and consulted on numerous campaigns across the nation at local, state, and federal levels. In high demand with the news media, Johnson was one of the only Republicans who successfully predicted the nomination of John McCain in 2008 and that Alaska Governor Sarah Palin could emerge as his running mate. He has been noted for his strategic analysis and early warnings that the Republican Party was in danger for betraying conservative principles. Johnson has appeared on CNN, CNBC, FOX News Channel, the BBC, and Bloomberg Television for his political expertise, as well as in numerous publications such as Human Events, National Journal's Hotline, the Wall Street Journal, USA Today, and beyond our borders with England's The Guardian and Columbia's Semana, and France's Agence. In 2004, Johnson developed a new arm within the already established political division that would provide polling results for candidates, advocacy groups, and corporations. Today Strategic Vision polls for such organizations as the Milton and Rose Friedman Foundation, Indiana Soybean Alliance, and the Institute for Justice. Strategic Vision's polling results have been identified as some of the top in the nation, regularly ranking among the most accurate as they were for the 2004 Presidential election for the states of Florida and Ohio. The company's polls have been listed in publications from Newsweek to local daily newspapers nationwide and is considered the 'official pollster' for the state-wide political television show, The Georgia Gang.

http://74.125.155.132/search?q=cache:0p8mHEMnMVYJ:www.redcounty.com/user/496+David+E.+Johnson+Jeb+bush&cd=1&hl=en&ct=clnk&gl=us&client=firefox-a

[Jackpine Radical]

24. I just love the way those fuckheads operate.

The Republicans prefer to stop recounts to keep their frauds masked. FL 2000, anyone? OH 2004? All the others? Anybody remember 18181 or whatever the hell it was in TX?

[BetterThanNoSN]

21. Hmmm...

Let's see if Frank Luntz can do a poll to see if this is fraud!

[berni_mccoy]

26. DEFUND STRATEGIC VISION LLC! STOP USING THEIR POLLS IN CONGRESS!