Skip to comments.Skewed and Unskewed Polls
Posted on 09/24/2012 7:36:30 AM PDT by for-q-clinton
In most all things, I try to follow Hanlons (or Heinleins) Razor: Never attribute to malice that which is adequately explained by stupidity.
This is particularly important to remember when looking at polls, Sometimes, however, one must wonder.
As I pointed out yesterday, the result of Romneys really bad week was that Romney had gone from 5 or 6 points behind in Gallup, to essentially tied. Even so, a number of people have noted that there are some odd assumptions in that poll, and others. Pat Caddell and Doug Schoen talked about it recently. Asked if the polls were, in his opinion, a fair representation of the electorate, Schoen said:
The simple answer is no John. The bottom line is there were seven percent more Democrats in the electorate in 2008 than there were Republicans. Thats from the exit polls and thats about as accurate as you can get .President Obama won by about seven points. Given 90 percent of Democrats vote for the Democrat and 90 percent of Republicans vote for the Republican, every time you reduce the margin between the parties by one point, roughly its about one point off the margin.
Schoen pointed out that the Pew poll was based on Democrats sampled for having an 11 percent voters registration edge over Republicans. He further added, saying that America has gotten more Democratic than 2008, which is a questionable assumption.
In fact, Rasmussen keeps a running monthly poll of party identification. In the latest poll, released September 1, they found:
During August, 37.6% of Americans considered themselves Republicans. Thats up from 34.9% in July and 35.4% in June. Its also the largest number of Republicans ever recorded by Rasmussen Report since monthly tracking began in November 2002.
Other polls including Gallup apparently have similar assumptions (called turnout models) in their polls.
There is a new website, called unskewedpolls.com, that basically reweights the data to fit the Rasmussen party identification. Their results are quite different, giving Romney somewhere between a five and eleven point lead.
Now, this should also be taken with a grain of salt. Basically, they claim (by the site name) to be an unskewed poll. In fact, theyre just a differently skewed take on existing polls. Instead of taking their numbers over, say, Gallup, though, what it should tell us is that even if the polls are being heavily weighted to Obama, Romneys still essentially tied. Any difference in Romneys direction in real turnout from the pollsters assumptions would bring Romney into a lead.
This will give the MSM another thing to get their panties in a twist about.
It costs someone a lot of money to do a poll. What benefit does the sponser get from it?
So why do pollsters play this game in the first place? First of all, they want to perpetuate the "horse race" as long as possible. The closer the race, the more people will pay attention to their polling and the more media coverage they will get.
It's like a real horse race. If it is a close race, the entire audience will be on their feet right to the end, paying close attention the entire time and yelling and screaming. If however, one horse gets way ahead, then many patrons will lose interest and start heading to the exits to place their bet on the next race.
Second of all, the pollsters realize that many Americans have a "bandwagon" mentality. That is, if one candidate gets too far ahead, then many will jump on the bandwagon, turning perception into reality. Most pollsters don't want Romney running away with this thing so they are keeping it as close as they can, as long as they can, in the hopes that those who would otherwise support Romney start getting frustrated and demoralized, allowing Obama to sneak away with an undeserved victory.
- iPhone5 - 5 Million Sold
- (less than expected???)
but SOLD OUT until October?
- Estimates has been as high as 10 Million iPhone5s per IMUS at FFC just now
- Rumors of APPLE going to $800 - $1000
- (when? see APPLE history graphs)
- $700.10 Closing
- $685 (about) Bid/Ask
- I expect Rush Limbaugh to rave about the new iPhone5 today - Rush is APPLE*s biggest free booster
]- I am waiting for Stuart Varney on Fox Financial Channel to cover the drop in APPLE stock prices -
Here it is:
$684.78 Opening MONDAY Sept 24
- For not hitting 10 Million in iPhone5 sales so far?
- Suggestions that APPLE only released 5 Million iPhone5*s to create long iPhone5 buyer lines for the TV news -
- The APPLE/Foxtone factory in China is CLOSED - Army is there guarding the factory - workers seen outside on TV today - not causing the drop in APPLE stock per FFC:
I don*t know beans about this -
- But APPLE has been a SOLID profitable company over the years
Rassmussen Polling (based on 2004)
Obama is up 1% (of LIKELY VOTERS)
Weighted/Polled (based on 2004):
39% Democrat (oversampled 3%)
Other Polls (of REGISTERED VOTERS)
Obama is up 2%
According to Pollsters In 1980 - Jimmy Carter was up 10% over Ronald Reagan just 2 weeks before the Reagan landslide
Remember 2000 Gore won Popular Vote - lost the Electoral College Vote - The media had announced NW Florida vote projections early - well before the rest of the US had even finished voting - and Al Gore promptly then withdrew his - in 2000 over 25,000 in Florida illegally voted - and were counted! - SCOTUS decided GW Bush won in Florida by just a few hundred votes -
But you all know how that turned out!
- Remember 2004 - Kerry was projected by the media to have won Ohio - based on “exit polls” taken by the media - “PUSH POLLS” I call them
But you all know how that turned out!
- Obamacare was passed by just one (1) vote - because a former Saturday Night Live commodian - confessed “Cokehead Al” had several extra recounts - now proven to have included over 5000 illegal votes that were counted
Watch: Massachussetts in the Senate:
(R-MA) Scott Brown against the “affirmitive action” “Cherokee Princess” (D-MA) Elizabeth “High-Czechbones” Warren (she still refuses to meet with American Indians to explain and justify how and why she “checked the box” at Harvard and even before that to gain an AA advantage)
EXACTLY. They WANT to control the narrative.
“We are seeing a DRAMATIC swing away from Obama. The American voter wanted to buy in to Hope and Change. Obama did not deliver. Another note, WHITES in UNEXPECTED(bottoms up!)numbers turned against the first black(half)President ever. It is yet to be determined if there is a racial component. LOOK FOR polling on that in the coming weeks.”
What on earth are you talking about with Apple? Please keep it on topic.
Internals matter. Likely voter projection models are, in essence, guesses. Often intelligent and educated guesses, but still guesses.
So, which guesses look better than others? Outside of first-time voters, those who did not vote for Obama in 2008 and will vote for him in 2012 is as close to an empty set as you’ll ever fine. But there is plenty of anecdotal evidence that Obama 2008 voters will either stay home or vote for someone else in 2012. As such, it’s hard to imagine Obama getting the same party edge in 2012 that he got in 2008, and certainly not higher.
On the flip side, 2010 was just shy of a “wave” election, with a dominant Tea Party turnout. While it is possible for Republicans to meet or exceed that turnout in 2012, a safer assumption might take 2010 as the GOP ceiling.
Based on that, if I were looking for a worst-case GOP/best-case ‘RAT number, I’d look at turnout being slightly more ‘RAT than in 2010. I’d cap the range of my analysis on the other end using 2010 turnout numbers. So, for a single result, I’d say 2010, adjusted +1% to the ‘RAT side.
News stories which drive interest and therefore/readership and viewership.
I don’t buy the horse race lies they spin. Sure that’s one small aspect of it, but they also want to help Obama by discouraging Romney’s voters.
But in fact I think they end up helping them because the lazy democrat voter will stay at home thinking their guy will win. But the broken glass Republican voters will turn out no matter what. They are applying the logic that turns off their voter. But I guess if they show it a tight race that may motivate their base to vote. But even then if they are skewing 5+ points it’s hard to make that up in just enthusiasm—especially when their voters are typically lazy.
Not sure I follow your last paragraph. Are you guessing polls are skewed in 2012...if so how much?
I’m saying I would use a range of weighting to reflect likely best/worst cases for each side. I don’t have the numbers on hand at the moment, so I’m using fairly generic descriptors to say that I expect turnout to be somewhere between 2008 and 2010 numbers, but close to 2010.
On the whole, Rasmussen is the only pollster whose turnout model has been along those lines, though Gallup seems to be zoning in on those numbers now, as well — it’s harder to tell there, because they’re still using registered vs. likely.
But these polls showing D+7 or higher are patently ridiculous.
Conversely, “overt” over-sampling, tends to gen up enthusiasm for the one being slimed so to speak.
This election, the nobama crowd is having significant trouble getting their base enthused, so whatever micro-managing they can do to gen up their 2008 support they do, even moochelle dragging up slavery and the Underground Railroad. Just because they beat the heck out of mclame, doesn't mean they are election geniuses in a real election. One’s record is hard to run against and nobama's base didn't see the change they were promised. Sort of back to the old adage, "fool me once, your fault, fool me twice, my fault.
First, make being a Republican mean something ~ compulsory tests for candidates!
In 2000 the media held the Bush DUI story until the weekend before the election to try and sabotage the GOP.
In 2004 they manufactured a phoney Bush National Guard story to try and sabotage the GOP
In 2008 the Media corruptly coordinated coverage with the Obama campaign via the Jour-0-List website.
Why do Conservative think that corrupt hyper partisan mindset in the media vanished this year?
There is ONE reason for these polls. Depress GOP fund raising and turn out. Do not be fooled.
My memory says Campaign Carl Cameron broke that story. Is that a faulty memory?
If correct, this says don't expect any protection from Fox. They'll break a story without regard to party.
Very nice website.
I was looking for a “contact me” link on it since I have a simple suggestion for the writer which would make it even better. Do you have such a link/EMail addy?
i don’t :-(