Getty Images
The 2008 election turnout model isn't being used to skew 2012 polls.
We talked the other day about poll denialism, and the notion, widely embraced among Republicans, that all major-outlet polls have been skewed as part of a conspiracy to boost President Obama over Mitt Romney. It's a pretty silly argument, but it's hard to avoid.
And while it's easy to mock those who feel the need to create their own reality, there was one aspect of conservatives' complaints that seemed more plausible than the rest: it's a mistake for pollsters to rely on the 2008 turnout model.
As the argument goes, the political landscape has changed quite a bit over the last four years, so there's no reason to assume the electorate will be nearly identical. To rely on a turnout model that's bound to be different necessarily leads to "skewed" results.
Sounds reasonable, right? The problem, though, is simple: as Nate Cohn explained, major pollsters aren't relying on the 2008 turnout model.
Most pollsters don't weight their polls to match a preconceived electorate. Instead, they take a demographically representative sample based on actual figures from the US census and then let respondents speak for themselves about whether they're voting for Obama or Romney. For illustrative purposes, consider the Bloomberg/Selzer poll. They started by taking a sample of all American adults, weighted to match the demographics of all adults in the US census, like, race, education, and marital status. To produce a likely voter sample, they then would have excluded adults who weren't registered to vote and then asked a series of questions to help determine who was likely to vote.
Ultimately, Selzer's sample found Obama leading by 6 points, by 49-43. Whatever you think of the outcome, it wasn't the result of Selzer imposing her assumptions upon the sample; she let her sample speak for itself. Did she take a good sample? We'll find out on Election Day. But if she's wrong, it won't be because she used the "2008 turnout model."
And what about the notion that Democrats are being over-sampled? Cohn explained why this is wrong, too.
But the fight over the validity of polling is itself illustrative of a larger issue.
Kevin Drum had a sharp piece on this this morning, noting the distinction between how the left and right have dealt with polling data they don't like.
On the left, we saw Nate Silver "dug deep into the minutiae of how polls are put together and how they're conducted, writing lengthy, table-laden posts that often meandered through several thousand words." On the right, we saw the emergence of "UnSkewed Polls," which reweights to Rasmussen -- because the other polls are part of a partisan conspiracy -- and "doesn't even pretend" to apply any rigor.
This is, to put it bluntly, nuts. And it suggests a fundamental difference between left and right, one that Chris Mooney wrote about earlier this year in The Republican Brain. Neither side has a monopoly on sloppy number crunching or wishful thinking, but liberals, faced with a reality they didn't like, ended up accepting reality and deciding to learn more about it. That's the Nate Silver approach. Conservatives, faced with a reality they didn't like, invented a conspiracy theory to explain it and then produced an alternate reality more to their liking. It's a crude and transparently glib reality, but that's apparently what the true believers want.
Leave a Comment:
"...Conservatives, faced with a reality they didn't like, invented a conspiracy theory to explain it and then produced an alternate reality more to their liking."
In the real world, the conservative brain does not accept change, which means that they are perpetually denying what is and living in fear of that change. It is a shame really for US all, because their denial of reality keeps US all in a cage unable to move forward yet they still glorify a past that never was.
Or they can just tune into Faux nooze , "Where we serve up reality more too your liking"
Excuse me, conservatives didn't come up with the alternative reality of Communism and proceed to kill tens of millions of human beings when they didn't conform. The left has absolutely no room to point fingers about alternative reality.
Meanwhile there is only one poll that counts.
Right off the rails today, aren't you, Shooter...
They've been living in a bubble all their lives, it's why they're who they are, as little Pooper demonstrates every time he comes over here to pee on the fire hydrants.
Shooter, when actual Communists walked the earth conseratives and liberals alike opposed them. In fact liberals probably opposed them with greater intensity. After all Nixon went to China not Johnson. :)
Shooter your right.
There is only one poll that counts - 6 Nov 2012.
By taking away the vote from the citizens that disagree with them, the Republicans currently in office are trying their best to insure that this poll is skewed.
You may want to look at the turn out for the 2010 Election. Turn out was about equal for Dems and Repubs. Do you really believe people are as excited to vote for the first black President as they are today with an unemployment rate of 8.1%? Independents will determine this election and currentlt they are about 5% in Romney's favor.
Oy, the dumb! Ok, let's give it a try.
1) What was the total number of Republicans who voted in 2008?
2) What was the total number of Republicans who voted in 2010? Was that number equal to, or greater, than the number of Republican voters in 2008?
3) You have ten minutes...
4) And your answer is?
//crickets//
It is a tale told by an idiot, full of sound and fury, signifying nothing. Mitt, Hannity, Rush,Colter and the rest of the peanut gallery are competing to be the idiot. Thanks Will Shakespeare.
Silly, but as deliberate ignorance of statistics go, nothing can top "this is not a scientific survey, it's a random survey." http://www.washingtonmonthly.com/political-animal-a/2012_05/this_is_not_a_scientific_surve037451.php
At this point, when I find that someone is a Republican, I just assume they're mentally ill in some way. Then, it's just a matter of finding out what particular derangement afflicts them, usually chosen from religious mania, paranoid delusions, or sociopathy.
Religious mania these people don't even properly follow their own religious beliefs the right way. They must have been brainwashed in some really bizarre way I think.
One of the biggest hypocritical things and con jobs that has been seen on TV was when there was one of these so-called religious groups ask people to send $10,000 and that religious group would pray for them. Now who was stealing from whom there.
I guess when someone tells you (or you tell yourself) that god is on your side, you begin to think that everything you do is righteous. . . that's why religion should be kept as far away from government as possible.
They believe that it is money that will save them from the mess they have made. And they have hired The American people as their maids.
Don’t blame Romney for all these things he says or all these accusations that are going around. What did Romney get a new brain, when he hasn’t spoken up against all this racist talk and lies about everything he says. These excuses these Republicans, extremists of hatred, and extreme wealthy make just keep getting dumber don’t they. When it is these very people, Romney and Ryan included, are causing it all. Just some more ridiculous excuses with no merit or truth. The stench just keeps getting deeper and deeper with these Republicans, extremists of hatred, and extreme wealthy.
Deb, I agree with everything you say except for the extremely wealthy part. If memory serves me correctly, isn't about 30% of the infamous 47% of 'non-taxpaying moochers' (as Romney describes them) Romney supporters?
My dad used to say "There are two kinds of Republicans: the very wealthy and the very stupid." I had kind of forgotten that until the last couple of election cycles, and I have to now, once again, acknowledge the 'old man' was correct.
The other day, someone (I think it was Steve) was asking why they're bothering trying to discredit the polls. Steve pointed out that, if Republicans really believed Romney was winning, they'd appear a lot more energetic than they do. I've been thinking about it, and I don't think this is about winning the election. I think they're already laying the groundwork for continuing to delegitimize President Obama in the future. The birther stuff has fortunately lost some of its salience, but if they can convince their right-wing bubble that the polls are wrong and Romney is really winning, then when Obama does win they'll be receptive to claims that he somehow "stole" the election. In other words, get ready for more unhinged and unsupported claims that Obama didn't earn the presidency (he got it because he thought he was entitled to it!). As if the ACORN garbage wasn't bad enough.
Or with all the other voter crap going on everywhere republicans are in charge and with the easily manipulated machines and scanners they have to have a believable story for their base so it'll all make sense when Romney manages a squeaker. They need the polls to be a bit closer in Ohio, but....
There is no way Florida is going to be on the up and up and probably others as well. A whole lot of suppression, stir in a good bit of TP poll watching and fear, with that last dollop of skewed results or "darn, missing votes" and voila - Romney and disaster.
Sorry, but I am seriously worried.
at the risk of sounding paranoid (you do a bit when describing people who are) You have to think that everything they do is at least on some level strategic and this like the voter regestration shenanigans in Fla. force the whole process to be called into question and scrutinized which automaticaly introduces the question of doubt that these people need to maintain thier narative. Take the birther stuff. None of the serious players on the right actualy believe it but they are willing to have the (for lack of a better word) rabble believe it and continue to opperate against thier own best interests. Like I said it sounds a machiavellian and little paranoid but consider the people we are talking about.
All right there in "When Prophecy Fails," Leon Festinger's classic study of cognitive dissonance. (His students infiltrated a UFO doomsday cult and watched what happened when the predicted end of the world failed to happen, which would be problematic under modern ethical standards, but, hey, this was the 50s.)
Nothing Republicans believe is fact-based, including going back to their Christianist mythology of all the thousands of Christians martyred by the Romans (it only happened a couple times - once under Nero, and non-Christian Romans were so disgusted it led to his downfall, and once under Domitian with the same result - most of the Roman dislike of Christians was the same kind of dislike we here have for idiots like Tony Perkins and the rest of the Xtian Right).
All you have to remember is: The Right is wrong.
Kind of reminds me of the debate between evolution and creationism/intelligent design.
It is simple the conservatives are in the first of the five stages of Grief.
-Denial,"this can't be happening to me." why aren't other seeing or think like us?
-The second,which is Anger will manifest itself after the debates."why us?", feelings of wanting to fight back.
-The third, Bargaining--This will manifest itself a week before the election when everybody must come to their senses, that the defeat would be inevitable and that Romney is nothing but a fraud who stands for nothing, who believes in nothing,besides his thirst for power.
-The fourth is Depression-overwhelming feelings of hopelessness, frustration, bitterness, self pity etc.The blame game will begin and Romney would be grilled in the court of conservative Opinion.
-i won't include the last one,which is Acceptance.Because movement Conservative will not accept a Democrat's victory,let alone that of a mixed race,kenyan socialist-communist-marxist-muslim-antichrist-crackhead-homosexual
khayyam
Stephen Colbert did the 5 stages of grief for Romney supporters this last Tuesday night it was hilarious!
http://www.rawstory.com/rs/2012/09/26/colbert-romney-supporters-beginning-to-cycle-through-5-stages-of-grief/
Thanks for the link!! i missed that.
It seems universal to losing electoral campaigns to downplay, deny, and question the validity of the polls that show them down. It is pro forma to remind us all that the only poll that counts is in November, blah, blah, blah.
Meanwhile gang, it ain't in the bag yet.
I think there are too many variables for the number crunchers and polls to be accurate, sure they could get lucky...50/50, either side isn't banking on ti, so what difference does it make?
Chris Mathews showed a clip of pig face telling his radio heads, "don't listen to these polls, the Dems want you to believe the race is over so, stay home, don't vote!"
That could go both ways, meaning if some Dems thought President Obama was WAY, WAY in the lead, they to might kick back and stay home.
Polls are useful for the campaigns. They are of no use for voters. We simply must go to the polls and vote our preferences. Let the professionals in the campaigns chew over whatever the 20 or so national polls might be indicating. Our job is simple. Vote!!
The poll that Limbaugh and Hannity et al, like is Rasmussen, which is always four or five points in Romney's favor over what the other polls have, whether it is national polling or swing state polling. So who is right? Well, just look at 2008. Guess what? Same thing. Rasmussen was four or five points behind the others in favor of McCain AND was four or five points behind what Obama got in the swing states. I think someone at MSNBC ought to bring this up and show it to everyone. Either Rasmussen's method is skewed permanently (that is, he is not correcting for what is a demonstrated shortcoming or bias in his surveys), or he is being paid to make the race look closer than it is.
Let's look at 2008 swing states. In OH Rasmmuseen had the race tied, O won by +4. In WI Ras had O +7, result O +14. In NV Ras O +4, result O +12. In PA Ras O +6, result O +10. In FL Ras Mc +1, result, O +2.5. In Mich Ras O +10, result O +16, In CO Ras O + 4, result, O +8.5. Someone on MSNBC ought to publish these numbers. I wouldn't mention it cept I'm tired of hearing how Rasmussen is the only accurate and unbiased pollster.
Caution this comment criticizes polling pundits.
Polls can be bought, if they show Obama ahead weeks on end, the Obama people can go to sleep, and you can't vote while sleeping. Hence a suppression of democratic turnout, while the conservatives base turn out a surprise.
(Is that so hard for pundits to understand? I did take a poll, no? If I took a poll would I be convinced the poll as right, only if I paid for it or if I was paid to take the poll? The poll taker is no different than anyone else, "they's pinions come from the same place as their cornpone". [You opinions come from the same place that makes your living.])
If the polls were based on the public recognition of real problems, finding real solutions, and never taking "no" for an answer, we might make lot of progress in hurry. The polls showing a 47/53 split mean nothing when the informed voter as polled showing at 80/20 split it is a call for action. The final poll on Election Day will be a 50.1/49.9 split and NO is the answer.
The polls used in the special swing states, are especially damaging to the nature of democracy when selecting only nine states and key districts to predict the Electoral Vote. This obviously derails the other 41 States, not because they can be predicted, but because in being predicted, the rest of the down-ballot offices and issue are short changed.
(Is this so hard for pundits to understand? (Is that so hard for pundits to understand? I did take a poll, no? If I took a poll would I be convinced the poll as right, only if I paid for it or if I was paid to take the poll? The poll taker is no different than anyone else, "they's pinions come from the same place as their cornpone". [You opinions come from the same place that makes your living.])
If the pundit's poll for Electoral Vote, make the pundits life easier, fulfilling, satisfying, and well paid, then should not the pundits have liability insurance to cover the cost of bad decisions made in the 7,800 other offices decided in this election. This is not the fault of the Electoral College, but the failure of pundits to understand that those 435 Representatives and the 100/3 Senators are more important and that 100/3.
(Is this so hard for pundits to understand? Polling the country to death has created the a government free to discard those voters?)
(Is this so hard to understand?)
If they are over-sampling Democrats it may be somewhat prophetic. With the time left, Romney could easily scare away that many voters
Doug you sound so childish! I asked a simple question, do you believe the turn out in this election will be the same as 2008. I'm inclined to believe you don't or you would have responded differently. In 2010 the Democrats lost control of the House I could care less how maney were Repubs and hoe many were Dems it's the results that should concern you.
The national debt is now over 16 Trillion and unfunded liabilities is over 100 Trillion. Do you know what your share is? It's 1 million dollars for every tax payer and you may want to give some thought to were we"re headed or due you still have you head in the sand.