Are we too sensitive to partisan skew in polls?

posted at 9:21 am on September 25, 2012 by Ed Morrissey

Critics of media polling have long complained about the sample skew that tends to favor Democrats in their surveys.  We do a lot of poll analysis here at Hot Air and we routinely compare the modeling to exit polling in past elections.  National Journal reports today that pollsters, especially those who work with media outlets, have begun to fight back against the criticism leveled by conservatives of institutional sample skew, claiming that they’re seeing trends on the ground that previous electoral models won’t capture:

Critics allege that pollsters are interviewing too many Democrats — and too few Republicans or independents — and artificially inflating the Democratic candidates’ performance. Pollsters counter that the results they are finding reflect slight changes in public sentiment — and, moreover, adjusting their polls to match arbitrary party-identification targets would be unscientific.

Unlike race, gender or age, all demographic traits for which pollsters weight their samples, party identification is considered an attitude that pollsters say they should be measuring. When party identification numbers change, it’s an indication of deeper political change that a poll can spot.

“If a pollster weights by party ID, they are substituting their own judgment as to what the electorate is going to look like. It’s not scientific,” said Doug Schwartz, the director of the Quinnipiac University Polling Institute, which doesn’t weight its surveys by party identification. …

On Monday, the news website Buzzfeed interviewed a Virginia-based blogger who re-weights public polls to reflect the partisan trends reported by automated pollster Rasmussen Reports. Dean Chambers, the blogger, then presents the adjusted data in charts on his website, unskewedpolls.com.

As of late Monday, Chambers’ website claimed that an average of polls conducted since Labor Day show Mitt Romney leading Obama, 52 percent to 44 percent. The website and its findings were trumpeted on the Drudge Report, the conservative-leaning news-aggregation site that has tended to highlight polls more favorable to Romney and less favorable to the president.

The pollsters claim that they’re seeing a big shift towards identification with the Democratic Party.  If so, then Gallup and Rasmussen have both missed it.  Both organizations routinely do general-population polling for partisan identification.  In fact, the latest state-by-state polling from Gallup (August 2012) shows that the shift has gone the other way:

Thus far in 2012, the two major parties have been closely matched nationally in terms of the absolute number of states each can claim as politically favorable, representing a dramatic change from 2008 and 2009 when the Democratic Party had an overwhelming advantage on this score. This doesn’t translate directly into likely election outcomes, given differences that can exist between the party leanings of adults versus registered voters, as well as differing turnout patterns and voting behavior of Republicans vs. Democrats in some states.

Polls are intended to be predictive.  In order to be predictive, the sample has to hew closely to the turnout model of the actual election. The best way to calculate that is to check the trends from the most recent election cycles.  One can get surprised by this when turnout shifts dramatically, as it did in 2008 — but that was in favor of the Democrats for a D+7 result, and it’s unlikely to happen a second time, especially after the all-even turnout model from the 2010 midterms.  That means that D+11 on national samples aren’t going to be terribly predictive of the outcome in November, nor would R+11 samples, and so it’s difficult to take those results seriously.  Furthermore, with just a few weeks before the election, pollsters need to start finding likely voters rather than just registered voters or general-population samples if they expect consumers to rely on them for predictions of voter behavior — again, the entire point of polling.

If there is one valid criticism of conservative poll analysis, it’s that we tend to focus on just party ID rather than a broader range of demographic categories — gender, age, income, and geography.  Most of that data exists in exit polling, too, so it isn’t terribly difficult to check, but it is time consuming.  However, if a national poll features a turnout model of D+11 or R+11, that’s enough to make the results unreliable without checking the rest of the demos, just as one with 60% men would be.

The pollsters complaining in this piece sound as though they resent the idea of having their models put into question at all.  They want consumers to simply swallow what they deliver without asking any questions.  If so, they’re relying on an outdated media-consumer model.


Related Posts:

Breaking on Hot Air

Blowback

Note from Hot Air management: This section is for comments from Hot Air's community of registered readers. Please don't assume that Hot Air management agrees with or otherwise endorses any particular comment just because we let it stand. A reminder: Anyone who fails to comply with our terms of use may lose their posting privilege.

Trackbacks/Pings

Trackback URL

Comments

Comment pages: 1 2 3

Which other candidate that ran in the primaries would be winning right now?

I’m asking a simple question: on what was the assumption that Romney was the “most electable” based?

Anybody that stays home or votes for Obama will share blame, period. You’re choosing four more years of this and that’s on YOU, no one else.

changer1701 on September 25, 2012 at 10:24 AM

So if Romney wins, do all those who stay home share in the victory?

ddrintn on September 25, 2012 at 10:28 AM

Check out this interview. Hugh Hewitt interviews a Marist pollster who recently published a D+10 poll in Ohio. The 2008 turnout in Ohio was D+8. Hugh maintains that there is no way that Democrats will meet or exceed their 2008 turnout, which was at the peak of Obama’s popularity. The pollster stubbornly insists that the 2008 turnout, plus or minus a few points, is completely scientific. I agree with Hugh Hewitt. No way Obama is going to meet or exceed what happened in 2008. If anything, in Ohio, we might see D+2 or D+3.

TarheelBen on September 25, 2012 at 10:29 AM

The jobs report sucked in August(and was revised downward for June and July). And BoA just announced they’re laying over 10,000 workers by year’s end. Which consumers are they talking to?

Doughboy on September 25, 2012 at 10:13 AM

We have recognized all along that defeating ANY incumbent president is serious, expensive and difficult business; and we indeed nominated the guy with the best chance to defeat Obama.

I expected the MSM to be biased, but I have not seen anything this unprecedented in 40 years; they don’t even PRETEND anymore to be fair. Zero objectivity.

Well, one thing to set aside: we don’t have to worry about Romney “peaking too soon,” as some of the conservative commentators worried about over the summer.

matthew8787 on September 25, 2012 at 10:29 AM

“We were doomed in 2004, here is a Fox news poll showing Kerry winning by 2 points the weekend before the election.

http://www.foxnews.com/projects/pdf/poll_012606.pdf

rob verdi on September 25, 2012 at 10:18 AM”

Here are the final polls in the Bush/Kerry race. Notice that Bush lead in the vast majority of the polls. And notice that the RCP average was within a point of the final margin…

Final Results – – 50.7 48.3 Bush +2.4
RCP Average 10/27 – 11/1 – 48.9 47.4 Bush +1.5
Marist 11/1 – 11/1 – 49 50 Kerry +1
GW/Battleground 10/31 – 11/1 – 50 46 Bush +4
IBD/TIPP 10/30 – 11/1 – 50.1 48 Bush +2.1
CBS News 10/29 – 11/1 – 49 47 Bush +2
Harris 10/29 – 11/1 – 49 48 Bush +1
FOX News 10/30 – 10/31 – 46 48 Kerry +2
Reuters/Zogby 10/29 – 10/31 – 48 47 Bush +1
CNN/USA Today/Gallup 10/29 – 10/31 – 49 49 Tie
NBC/WSJ 10/29 – 10/31 – 48 47 Bush +1
ABC/Wash Post 10/28 – 10/31 – 49 48 Bush +1
ARG 10/28 – 10/30 – 48 48 Tie
CBS News/NY Times 10/28 – 10/30 – 49 46 Bush +3
Pew Research 10/27 – 10/30 – 51 48 Bush +3
Newsweek 10/27 – 10/29 – 50 44 Bush +6

gumbyandpokey on September 25, 2012 at 10:26 AM

That “Kerry led Bush right up until the election” myth will go on and on and on and on and on.

ddrintn on September 25, 2012 at 10:31 AM

You trot out an Obama 47% poll to say that he will win?????
faraway on September 25, 2012 at 10:20 AM

Well, I’ll take the 53-47 Romney victory.
:D

whatcat on September 25, 2012 at 10:31 AM

So if Romney wins, do all those who stay home share in the victory?

ddrintn on September 25, 2012 at 10:28 AM

Those whom would stay home with this nation’s survival on the line deserve nothing.

viking01 on September 25, 2012 at 10:32 AM

“That “Kerry led Bush right up until the election” myth will go on and on and on and on and on.”

I think that’s because of the goofy exit polls that got ingrained in people’s heads and they confuse those with the pre-election polls that clearly predicted a close Bush win.

But I do admit I didn’t remember that Reagan had taken the lead over Carter in September in most polls and just blew the election open in the end. Probably due to the fact that Gallup was the most visible pollster at that time and polls overall didn’t get as much publicity.

gumbyandpokey on September 25, 2012 at 10:34 AM

This isn’t 1980, and Romney most certainly is NOT Reagan.
ddrintn on September 25, 2012 at 10:26 AM

However, Obama most certainly is Carter.

whatcat on September 25, 2012 at 10:35 AM

OT: How embarrassing. Barry stands in front of the UN and says that we (the government) had nothing to do with the anti-Muslim video. Thanks Barry, I’m sure this will fix everything.

TarheelBen on September 25, 2012 at 10:35 AM

Those whom would stay home with this nation’s survival on the line deserve nothing.

viking01 on September 25, 2012 at 10:32 AM

So, “nothing” would mean neither praise nor blame. What about those who vote for neither Obama nor Romney?

“Vote for our icky moderate nominee or the universe will implode!!!!” Some people are tired to death of THAT as well.

ddrintn on September 25, 2012 at 10:36 AM

Pollsters make big money generating this trash and they’re not going to let go easily.

rplat on September 25, 2012 at 10:37 AM

I’m asking a simple question: on what was the assumption that Romney was the “most electable” based?

His campaign infrastructure and his fundraising. Like it or not, none of the alternatives had anything approaching that, to the point where some couldn’t even manage to get on the ballot in states like VA. My choice in the primary was Romney…or Ron Paul. That’s not difficult.

And I asked a simple question, too…who among that group would be doing better at this point?

So if Romney wins, do all those who stay home share in the victory?

ddrintn on September 25, 2012 at 10:28 AM

If it’s Obama voters, sure.

changer1701 on September 25, 2012 at 10:38 AM

However, Obama most certainly is Carter.

whatcat on September 25, 2012 at 10:35 AM

Which is irrelevant while there isn’t a Reagan-like stand-in.

ddrintn on September 25, 2012 at 10:38 AM

OT: How embarrassing. Barry stands in front of the UN and says that we (the government) had nothing to do with the anti-Muslim video. Thanks Barry, I’m sure this will fix everything.
TarheelBen on September 25, 2012 at 10:35 AM

Obama says it to keep the Muslims rioting and murdering, then he blames America and the First Amendment for the video again, ad infinitum. See how that works?

whatcat on September 25, 2012 at 10:40 AM

Every poll is rigged including the one on election day.

bgibbs1000 on September 25, 2012 at 9:39 AM

Excellent point . . . all those dead voters do tend to bias the samples.

rplat on September 25, 2012 at 10:40 AM

His campaign infrastructure and his fundraising.
So if Romney wins, do all those who stay home share in the victory?

LOL, come on. What a dodge. So why didn’t that campaign infrastructure and fundraising help him win in 2008? He outraised everyone else in the field, as I remember.

ddrintn on September 25, 2012 at 10:28 AM

If it’s Obama voters, sure.

changer1701 on September 25, 2012 at 10:38 AM

So which voters are under contract to vote for Romney regardless?

ddrintn on September 25, 2012 at 10:40 AM

One really interesting thing here in WI is that there is a distinct lack of lawn signs for either candidate. You see a few in the really partisan areas, but there doesn’t seem to be a ton of passion out there.

WI might be “electioned out” after the recall.

That surge in consumer confidence is amazing when you think about it. And the previous month was revised upwards, too. That might explain why voters seem to have decided to re-elect Obama.

gumbyandpokey on September 25, 2012 at 10:41 AM

gumbyandpokey on September 25, 2012 at 10:09 AM

Gumby, gumby, gumby, take a breath. Pollsters can predict how someone will vote but not that they will vote. Newly registered voters are an exception because they have been motivated to vote and they will….like the 1.2 million newly registered Evangelicals who vote Republican, many of whom yes, are in Ohio. To paraphrase a little Nancy Pelosi (God forbid): “We will have to wait for the Vote on Nov 6th to see what’s in the Vote”

And to add a little more chafe to your cheeks, Rasmussen has said this dead heat battle will turn on an event like 2008 and the fiancial crisis. I say in 2012 that event is Benghazi, Obama’s Waterloo, symbolizing his monumental foreign policy failures.

gracie on September 25, 2012 at 10:41 AM

ddrintn on September 25, 2012 at 10:36 AM

If you choose to be tired or lazy or whatever excuse comes to mind then expect nothing from your country just as if you had raised a white flag in Vichy, France when Germany invaded or raised one flag in Italy when the Germans occupied it and another flag after they had been chased out.

viking01 on September 25, 2012 at 10:42 AM

I have said it before but I think part of the reason that the demographics seem to tilt Democratic is fear.

I used to take the time to respond to these polls. I no longer do. I have seen liberal groups use information about your beliefs gathered from other sources to target those who disagree. Lawns and landscaping around me was vandalized during the last election over lawn signs. Folks were harassed at their places of work in CA over petition signatures. I fully expect some rabid supporters of some politician or cause to make use of fake polls to target those who oppose them. What promise of anonymity is there when someone calls you at your home?

Paranoia? Maybe, but I have nothing to lose by not helping some random pollster. And if I thought of this I am sure others have as well.

OBQuiet on September 25, 2012 at 10:42 AM

However, Obama most certainly is Carter.
whatcat on September 25, 2012 at 10:35 AM

Which is irrelevant while there isn’t a Reagan-like stand-in.
ddrintn on September 25, 2012 at 10:38 AM

Nope, people don’t want the worst President ever (Obama) for a 2nd go round anymore than they did the runner-up worst President ever.

whatcat on September 25, 2012 at 10:43 AM

But I do admit I didn’t remember that Reagan had taken the lead over Carter in September in most polls and just blew the election open in the end. Probably due to the fact that Gallup was the most visible pollster at that time and polls overall didn’t get as much publicity.

gumbyandpokey on September 25, 2012 at 10:34 AM

Yeah, I’m old enough to remember when it seemed that the only polling outfits anyone ever quoted were Gallup and Harris. Now it’s poll after poll after poll, wall to wall, 24 hours a day.

ddrintn on September 25, 2012 at 10:44 AM

Nope, people don’t want the worst President ever (Obama) for a 2nd go round anymore than they did the runner-up worst President ever.

whatcat on September 25, 2012 at 10:43 AM

Maybe, but would John Anderson have beaten Carter head to head?

ddrintn on September 25, 2012 at 10:46 AM

That surge in consumer confidence is amazing when you think about it. And the previous month was revised upwards, too. That might explain why voters seem to have decided to re-elect Obama.
gumbyandpokey on September 25, 2012 at 10:41 AM

Re-elect Obama because the multi-victorious, wildly popular Scott Walker lifted them from their misery? Yeah, that makes sense.

whatcat on September 25, 2012 at 10:46 AM

If you choose to be tired or lazy or whatever excuse comes to mind then expect nothing from your country

viking01 on September 25, 2012 at 10:42 AM

So “nothing” as in neither praise nor blame. Thank you.

ddrintn on September 25, 2012 at 10:48 AM

To all, stop fretting… Look at any poll and look at the way independents are voting… The actual vote would +/-2 of the indepedents vote… it is that simple… So in other words since Romney is winning the independents vote in almost every poll then Romney is going to win the elections…

mnjg on September 25, 2012 at 10:48 AM

Nope, people don’t want the worst President ever (Obama) for a 2nd go round anymore than they did the runner-up worst President ever.
whatcat on September 25, 2012 at 10:43 AM

Maybe, but would John Anderson have beaten Carter head to head?
ddrintn on September 25, 2012 at 10:46 AM

You make a good argument against the “let’s go kook-third party” case.

whatcat on September 25, 2012 at 10:48 AM

So “nothing” as in neither praise nor blame. Thank you.

ddrintn on September 25, 2012 at 10:48 AM

I have overestimated your intelligence and for that I apologize.

viking01 on September 25, 2012 at 10:50 AM

Re-elect Obama because the multi-victorious, wildly popular Scott Walker lifted them from their misery? Yeah, that makes sense.

whatcat on September 25, 2012 at 10:46 AM

In his race for the senate in that blue state, Thompson is trailing a far left-winger. A state in which unabashed conservative Walker won two elections in as many years. Think about that one.

ddrintn on September 25, 2012 at 10:51 AM

That “Kerry led Bush right up until the election” myth will go on and on and on and on and on.

ddrintn on September 25, 2012 at 10:31 AM

It is certainly not true at all that Kerry led right up until the election. However, Bush’s lead was not universal. Some polls had Kerry in the lead throughout. Dems, who couldn’t believe that anyone could vote for Bush twice, were holding out hope that there would be a late surge toward the challenger, just as we are now.

One important difference though from 2004 is that this time the incumbent is a Dem. Dems always underperform the polls and Repubs always overperform them. And, of course, there is the economy, which was humming along under Bush.

But we have to remember that even though Obama is supremely horrible, it is still very hard in the modern era to pick off an incumbent. Few incumbents have lost in the past century. I never expected Romney to open up a big lead and keep it. The party’s bases are around 40% – those numbers are almost unshakeable. The fight for the remaining 20% is fierce.

Missy on September 25, 2012 at 10:51 AM

You make a good argument against the “let’s go kook-third party” case.

whatcat on September 25, 2012 at 10:48 AM

Anderson wasn’t a “kook”, hje was a decent moderate guy. And you avoided the question. Since the 1980 election was ALL about evicting Carter, would you say Anderson would’ve beaten Carter head to head?

ddrintn on September 25, 2012 at 10:53 AM

ddrintn on September 25, 2012 at 10:48 AM

ddrintin is a shill who wants Obama to win — a troll — a democrat sent there to upset folks — he’s eminently ignorable — so ignore him — the more you respond the move his ilk gets into the thread — just ignore him and he may go away — but he’s so egotistical it may take some time.

rebuzz on September 25, 2012 at 10:55 AM

It is certainly not true at all that Kerry led right up until the election.

Missy on September 25, 2012 at 10:51 AM

No, Bush had a fairly consistent though small lead after a certain point, just as Obama does now.

ddrintn on September 25, 2012 at 10:57 AM

ddrintin is a shill who wants Obama to win — a troll — a democrat sent there to upset folks — he’s eminently ignorable — so ignore him — the more you respond the move his ilk gets into the thread — just ignore him and he may go away — but he’s so egotistical it may take some time.

rebuzz on September 25, 2012 at 10:55 AM

Translation: I ask tough questions which get at some truths that rah rah party-hack partisans would rather not think about.

ddrintn on September 25, 2012 at 10:59 AM

In his race for the senate in that blue state, Thompson is trailing a far left-winger. A state in which unabashed conservative Walker won two elections in as many years. Think about that one.
ddrintn on September 25, 2012 at 10:51 AM

RCP ranks it as a “toss up”. It’s not surprising the a seat that was held by a Dem would have built-in strong Dem support to be filled by another Dem who’s a current Congress member. It’s actually a little surprising that it’s even a toss up race, should be a Dem cakewalk.

whatcat on September 25, 2012 at 11:04 AM

I’m actually pretty grateful for this article. I was on vacation recently with friends, and I was trying to explain to one of them that you have to look at sampling for a poll before believing it. She had never heard of mirroring voter data or election results to get an accurate poll. So when she began looking she saw many were skewed. I’m finally seeing people starting to wake up a litte and its refreshing! I’ll be sure to pass this article around.

RadioAngel on September 25, 2012 at 11:05 AM

Awesome troll action on the threads today…my unofficial ‘troll poll’ says Dems are panicking and doubling down on ‘Operation Demoralize’.

Carry on.

Mitsouko on September 25, 2012 at 11:07 AM

Had the nation been stupid enough to elect populist John Anderson in 1980 with the Cold War as it was, Iran and the hostages as Peanut had left it, our defenses in shambles, misery index in double digits and economy on the skids the United States likely would have met the same fate as Biafra.

viking01 on September 25, 2012 at 11:13 AM

Right now, all these polls are eye-candy.

de rigueur on September 25, 2012 at 11:21 AM

So if Romney wins, do all those who stay home share in the victory?

ddrintn on September 25, 2012 at 10:28 AM

If after Nov. 6 they finally roll up their “HOPE” posters, move out of Mom’s basement, and get a job in Romney’s growth economy, you are damn right that they do.

Difficultas_Est_Imperium on September 25, 2012 at 11:21 AM

However, Obama most certainly is Carter.

whatcat on September 25, 2012 at 10:35 AM

Which is irrelevant while there isn’t a Reagan-like stand-in.

ddrintn on September 25, 2012 at 10:38 AM

Romney is worse the Reagan. Obama is worse than Carter. Assuming Romney IS better than Carter, these equations follows:

Reagan > Romney,
Carter > Obama,
and Romney > Carter, then

Romney > Obama.

Jurisprudence on September 25, 2012 at 11:25 AM

If after Nov. 6 they finally roll up their “HOPE” posters, move out of Mom’s basement, and get a job in Romney’s growth economy, you are damn right that they do.

Difficultas_Est_Imperium on September 25, 2012 at 11:21 AM

If Romney wins, and the economic turnaround is visible and palpable, he WILL win in 2016. The Democrats are quaking in their boots at having to run against another Morning in America campaign. They weren’t prepared then, and they’re not going to prepared for it should it happen, in the future. And Romney would deserve to run unopposed in the Republican primaries.

Jurisprudence on September 25, 2012 at 11:30 AM

You make a good argument against the “let’s go kook-third party” case.
whatcat on September 25, 2012 at 10:48 AM

Anderson wasn’t a “kook”, hje was a decent moderate guy.
ddrintn on September 25, 2012 at 10:53 AM

So marry him, then. I don’t care.

whatcat on September 25, 2012 at 11:31 AM

I’m sensitive to the whole idea of polling and the arrogance that any pollster thinks they can predict the future. Over 131 million people voted in the 2008 presidential election so if you think that polling of a miniscule “sample” can determine what that massive an amount of people will do at any moment in time, then you’re really really kidding yourself. Statistical analysis is busywork for people with nothing better to do who work for those who need an ego boost and we know how well politicians fit that description.

stukinIL4now on September 25, 2012 at 11:35 AM

These National Polls are almost meaningless at this point. We’ve seen a 1 – 3 point lead for Obama since the beginning of Summer.

What matters now are the swing states. That’s pretty much it. If the swing state polls show more than 3 points in favor of Romney before election day, he’s toast. Not being an Eeyore, just stating the facts.

Pray for rain on Election Day.

GadsdenRattlers on September 25, 2012 at 11:40 AM

Crap… I meant 3 points in Favor of Obama.

GadsdenRattlers on September 25, 2012 at 11:41 AM

So marry him, then. I don’t care.

whatcat on September 25, 2012 at 11:31 AM

Don’t think he hasn’t tried.

viking01 on September 25, 2012 at 11:41 AM

So marry him, then. I don’t care.
whatcat on September 25, 2012 at 11:31 AM

Don’t think he hasn’t tried.
viking01 on September 25, 2012 at 11:41 AM

Waiting for just the right time to pop the question, I’m guessing. Candlelight and a bottle of Maddog – gotta have the perfect setting, y’know.

whatcat on September 25, 2012 at 11:48 AM

Waiting for just the right time to pop the question, I’m guessing. Candlelight and a bottle of Maddog – gotta have the perfect setting, y’know.

whatcat on September 25, 2012 at 11:48 AM

It’s the restraining order that gets in the way and he still can’t figure whether it’s praise or blame….

viking01 on September 25, 2012 at 11:51 AM

Obama was in full on appeasement mode at the U.N. today. Jessica Yellin at CNN said he walked the ‘fine line between a domestic audience and an international one’ when it comes to that movie trailer. She then quoted what he said….

My point is that there is NO FINE LINE here. Freedom of Speech is a core American value which we should never waiver on, apologize for, water down, or excuse. This is the way it is.

MaggiePoo on September 25, 2012 at 11:52 AM

Apparently the trolls went to recess.

itsspideyman on September 25, 2012 at 11:53 AM

Translation: I ask tough questions which get at some truths that rah rah party-hack partisans would rather not think about.

ddrintn on September 25, 2012 at 10:59 AM

No translation needed — you are someone who has no real idea about anything but wants to get people upset — start your own blog and se if anyone reads it — until then you are a hack and I’m just trying to inform the good folks on HA that they are free to ignore you — ’cause they should — you’re not an honest contributor — you are a hack, a troll, a non-entity.

Carry on.

rebuzz on September 25, 2012 at 11:54 AM

As my Uncle Joe said: ‘Figures don’t lie. But liars sure can figure.’

The polls were skewed in 1980 and badly so – they missed the walking away from Carter until the last week of the campaign when Reagan magically pulled ahead… and yet the reporting hadn’t pointed to any major change right before that. It was all ‘Carter will be re-elected by a wide margin because Americans typically re-elect incumbents’. That was the last time I heard that meme and its had a cross over it since 1980.

When I see D+13 skews then something is highly suspect. There is very little marginal difference between D/R/I and anything that puts any part of that equation ahead by more than +5 is skewed, and skewed badly and a spread from top to bottom of 10 points is way out of kilter.

Basically the only polls to pay attention to are the weekly and monthly tracking polls that have a generally unvarying D/R/I breakdown over 6 months so that long-term trends can be analyzed. 3 day tracking polls give a point by point reading, but aren’t really indicative of very much save fluctuation of stories over that period. These one-shots are pretty much useless unless done by a local organization that has a good indicator of local breakdowns at the State level as they can miss stuff the big outfits don’t track well.

ajacksonian on September 25, 2012 at 11:57 AM

start your own blog and se if anyone reads it
rebuzz on September 25, 2012 at 11:54 AM

A lot of unintentional comedy blogs get read. People gotta get their laughs somewhere. And it’s even funnier when the person has no clue that he’s being laughed at, a la the Howard Stern/Jay-Walking dummy on the street videos.

whatcat on September 25, 2012 at 12:03 PM

Are there REALLY any undecided voters at this point? The polls say there are typically around 8% undecided.

I’ve asked the question “who you are voting for” to my facebook friends, family and coworkers. EVERYONE knows who they are going to vote for. I have yet to find ONE person who is undecided.

The closest I’ve come to an undecided voter are people who say “I’m pretty sure, I think” or don’t participate in the discussion.

GadsdenRattlers on September 25, 2012 at 12:07 PM

May also skew things to accept silence as a vote for Obama and more silence as a vote of high approval for Obama as the video showed of the answering machine that picked up the call and recorded the recording that was tallying the votes. Just sayin’…

UnderstandingisPower on September 25, 2012 at 12:07 PM

I want a t-shirt that says -

“Obama polling”

{this thread pic of Obiwan}

“these are not the samples you were looking for”

dissent555 on September 25, 2012 at 12:10 PM

Hmm..mmmmm…

Hamilton County, Ohio (Cincinnati) absentee voting is surging.

SouthernGent on September 25, 2012 at 12:10 PM

“…and we routinely compare the modeling to exit polling in past elections. ”

…as of about 6-7weeks ago, when we got excoriated for hem-wringing gullibility and started bothering to look.’

rayra on September 25, 2012 at 12:10 PM

I don’t know who will win but using an election from 32 years ago with a California, movie star, ex Democrat, Republican people actually really liked but didn’t think he was smart enough vs. a southern. Democrat who quite literally had an embassy being held hostage…. And using that as a basis of an argument …sounds at best suspect, desperate at worst.

Romney may win, there are still weeks to go, Reagan v Carter will have nothing to do with the outcome. Anyone under 50 today could not even have voted in that election.

NextGen on September 25, 2012 at 12:12 PM

Are there REALLY any undecided voters at this point? The polls say there are typically around 8% undecided.
I’ve asked the question “who you are voting for” to my facebook friends, family and coworkers. EVERYONE knows who they are going to vote for. I have yet to find ONE person who is undecided.
The closest I’ve come to an undecided voter are people who say “I’m pretty sure, I think” or don’t participate in the discussion.
GadsdenRattlers on September 25, 2012 at 12:07 PM

Yup, there are. If you watch election night interviews some voters even admit they don’t know as they are going in to vote.

The lion’s share of the undecided vote has historically gone to the challenger instead of the incumbent.

whatcat on September 25, 2012 at 12:13 PM

Hmm..mmmmm…

Hamilton County, Ohio (Cincinnati) absentee voting is surging.

SouthernGent on September 25, 2012 at 12:10 PM

That’s only part of the story….Republicans hold a 7,912 advantage over the Democrats in Hamilton County in requested absentee ballots.

Four years ago, it was the Dems with a 2-1 advantage.

sentinelrules on September 25, 2012 at 12:13 PM

Carter was “ahead” at the end of October.

rollthedice on September 25, 2012 at 12:15 PM

Look… as soon as people started relying on the RCP average of polls, the gig was up. Dems had to start doing D+10 to fudge the numbers.

faraway on September 25, 2012 at 9:39 AM

Bullshit. An average of garbage is garbage. GIGO. When you have 19 skewed poll and one accurate one, even averaging is useless. In fact I’ll go one further and declare RCP part of the overall fraud, a deliberate attempt to legitimize the push-polling and further influence public opinion. Like global warming advocates claiming to use science, while cherry-picking subsets of data to use or exclude.

rayra on September 25, 2012 at 12:16 PM

Actually Bush was up big against Kerry in 04 – but I believe not so much in ’00, in fact he trailed.

The only constant I can really find has been a flight from the incumbant to the challenger toward the end. So the needle will move towards Romney at the end, but by how much is unknown. This goes to the undecideds break to the challenger theory.

My only response to all the polling is that none of it makes much sense – some of it has been dilberately skewed to numbers that make zero sense. If Obama isn’t winning independents – according to Rasmussen and Gallup I don’t believe he ever has – and if he is losing catholics and the gender gap is only +4 it doesn’t correlate with what the polls are saying overall. I can just say that it may come down to ground game. I don’t think debates tend to move much and neither fdoes advertsing unless you can just drwon out the other guy – which Obama did to McCain but cannot this year.

So who the hell knows – as McCain was sliding last time, the internals – beyond just partisan splits – showed trouble. This year they don’t. Obama – according to the polls is set up to underperform to 2008 with every demographic except blacks, who are not as enthused – yet he is even on the total vote and ahead on the electoral. Very interesting.

Zomcon JEM on September 25, 2012 at 12:22 PM

Firstly, Ed, thank you for this post and THANK YOU FOR YOUR POLL ANALYSIS OVER THE PAST MONTHS AND YEARS. I think blame (credit) for the thesis of your post — “Are we too sensitive..” — can be laid at your feet. I mean this seriously and as a compliment. There are a lot of very smart commenters on this blog who are political junkies and who have followed your lead and become adept at detecting the Bravo Sierra the pollsters are pumping out.

We appreciate the caveats in this post but many of us remain unpersuaded when pollsters whine something like “you just do not understand our methodologies”.

Understand, Pollsters? Yes, we understand! We are just not in the market for manipulated numerological progaganda.

The War Planner on September 25, 2012 at 12:26 PM

Well one thing I noticed is that the Cleveland Ohio Democrats have lost over 100,000 registered voters since 2008……..

angrymike on September 25, 2012 at 12:27 PM

“Vote for our icky moderate nominee or the universe will implode!!!!” Some people are tired to death of THAT as well.

ddrintn on September 25, 2012 at 10:36 AM

I can say this. I was really ticked in 2008 when the GOP chose McCain as the candidate regardless of what conservatives wanted. When Romney got out of the race I felt the GOP forced him out and promised him “next time”. So in 2012 when conservatives were told that Romney was our candidate, I was even more upset – and dead set against voting for the GOP forced candidate.

Then I looked at the country. I realized that this election is the last possibility to save the USA in which I’ve been privileged to grow up in for my children and grandchild(en). I WILL vote for Romney and based on the above, I’d even agree to vote for Romney’s dog over Obama. Obama must be stopped from destroying America.

We can fight the “GOP elite picks the candidate” at a later date. Right now my vote is for America.

katablog.com on September 25, 2012 at 12:31 PM

“Vote for our icky moderate nominee or the universe will implode!!!!” Some people are tired to death of THAT as well.

then vote for Obama and be gone.

gerrym51 on September 25, 2012 at 12:36 PM

Katablog
amen……….

angrymike on September 25, 2012 at 12:36 PM

Bullshit. An average of garbage is garbage. GIGO. When you have 19 skewed poll and one accurate one, even averaging is useless. In fact I’ll go one further and declare RCP part of the overall fraud, a deliberate attempt to legitimize the push-polling and further influence public opinion. Like global warming advocates claiming to use science, while cherry-picking subsets of data to use or exclude.

rayra on September 25, 2012 at 12:16 PM

..actually it’s worse than garbage because it exacerbates the skew by putting the results of polls with sound internals on the same footing of those with flawed internals by merely averaging the two results. For example, a poll of the Chicago office of OFA and a poll of 3,000 likely voters in Oiho are not the same and the average results are wa-a-a-a-a-y skewed.

The War Planner on September 25, 2012 at 12:40 PM

It seems to me that what this pollster is saying is, “Hey, we’re just dialing numbers, and more democrats are answering. So it stands to reason that there are more democrats.”

However, there are a few problems with this line of reasoning.

First, a poll, even a poll of two thousand people within a single state, is statistically insignificant. There are hundreds of thousands of registered Republicans and democrats in Ohio alone, therefore if you were just calling randomly, or even semi-randomly, you’d be just as likely to dial up more Republicans as more Democrats. The fact that they’re consistently dialing more democrats in their polls, is in fact proof that some aspect of their polling is decidedly not random, and therefore is likely skewing their results.

The second problem with the idea that they’re seeing, “movement towards democrats, over that of 2008,” is because we have actual party registration to compare things too. Most states keep track of how many registered voters there are in each state, and what party they’re registered to. In the past four years, there has been incredibly significant movement in party registrations, so much so that in states like Iowa, registered Republicans outnumber registered democrats.

Of course, some people change their minds concerning what they, “think,” of themselves as, and do so quite frequently. So stat level registration isn’t the end all. However, it does give us something to compare polling too, so if Rasmussen and Gallop say Republicans have made big gains in the past four years, and official registration says that we’ve made big gains in the past four years, then we’ve probably made big gains in the past four years.

WolvenOne on September 25, 2012 at 12:41 PM

Josh Kraushaar ‏@HotlineJosh
Romney prob in nutshell: Staten Island #NY11 district filled w working-class Catholics: Obama 51, Romney 47. McCain carried CD 51-48% in 08.

gumbyandpokey on September 25, 2012 at 12:45 PM

BREAKING NEWS!!!!! HIGHEST PRIORITY!!

Madonna in concert last night in Washington, D.C. Verizon Center:

“We have a black Muslim in the White House. Is that some amazing sh*t or what?”

ericdondero on September 25, 2012 at 12:48 PM

Why the polls are tied…hilarious (sfw)

http://bit.ly/Ssg8IA

winston on September 25, 2012 at 12:49 PM

I would like to see a poll two weeks before of early voters. Those that have voted already and compare those percentages to the traditional polls at that time. Would be interesting – no?

WC on September 25, 2012 at 12:50 PM

These are not the samples I am looking for.

Move along.

TerryW on September 25, 2012 at 12:52 PM

“It seems to me that what this pollster is saying is, “Hey, we’re just dialing numbers, and more democrats are answering. So it stands to reason that there are more democrats.”

Sure. Makes sense. They’re all home answering the phone living on the dole.

WC on September 25, 2012 at 12:52 PM

Madonna in concert last night in Washington, D.C. Verizon Center:

“We have a black Muslim in the White House. Is that some amazing sh*t or what?”

ericdondero on September 25, 2012 at 12:48 PM

http://www.huffingtonpost.com/2012/09/25/madonna-obama-black-muslim_n_1912400.html

Language warning.

whatcat on September 25, 2012 at 12:53 PM

There are many sources of poll bias, and it’s difficult to correct for all of them.

Even here at HotAir, analysts try to correct poll bias by applying internals to partisan splits from previous exit polls. But the exit polls themselves skew toward the Democrats.

For example, exit polls showed Gore leading Bush by 6% in FL, and the race was a virtual tie. Exit polls showed Kerry leading Bush by 20% in PA in 2004, and Kerry won the state by 2%. Exit polls in 2004 also showed Kerry winning FL, OH, and VA, and Bush won all of them in the actual election. Exit polls also showed a tie between Walker and Barrett in the recent Wisconsin recall, and Walker won by 7%.

Perhaps exit pollsters tend to choose urban precincts (which tend to vote more Democrat than suburbs or rural areas) in order to get larger sample sizes. Or perhaps Democrat voters are more willing to talk to exit pollsters than Republican voters.

Steve Z on September 25, 2012 at 12:57 PM

New Poll just out, Romney Obama tied in Nevada.

http://battlegroundwatch.com/2012/09/25/all-tied-up-in-nevada-46-to-46-glen-bolger-public-opinion-strategies/

WolvenOne on September 25, 2012 at 12:57 PM

Today’s example: D+10 poll in Ohio shows a dead heat. In 2011, Gallup said Ohio was a D+1 state.

http://nicedeb.wordpress.com/2012/09/24/obama-and-romney-neck-in-neck-in-oh-poll-with-d10-sample/

These polls are junk.

Also, according to CNN’s 2008 national exit polling, 20% of the voters that identified as “conservative” voted for Obama. That right there was enough votes (6.8% of the total) to bring Obama to victory.

crosspatch on September 25, 2012 at 12:59 PM

“New Poll just out, Romney Obama tied in Nevada.

http://battlegroundwatch.com/2012/09/25/all-tied-up-in-nevada-46-to-46-glen-bolger-public-opinion-strategies/

WolvenOne on September 25, 2012 at 12:57 PM”

Isn’t he a Republican pollster?

gumbyandpokey on September 25, 2012 at 1:03 PM

Chris Matthews said yesterday that to use the word “apartments” is “racist”.

By Oct. 3, the first debate, he’ll say that “Mr. President” is “racist”.

Schadenfreude on September 25, 2012 at 1:03 PM

Seeing trends on the ground my azz…

There ain’t no +10 D (actually 10.4) happening.

catmman on September 25, 2012 at 1:07 PM

gumbyandpokey on September 25, 2012 at 1:03 PM

you never say “isn’t it a democratic pollster”.

lol

gerry-likes gumby because he’s obvious troll

gerrym51 on September 25, 2012 at 1:08 PM

I have overestimated your intelligence and for that I apologize.

viking01

It’s about time you got up to speed where ddumbo is concerned, lol.

xblade on September 25, 2012 at 1:12 PM

Here’s the Gallup Poll, Carter vs Reagan, 1980. It shows an 8-point difference in favor of Carter in late October.

http://www.thegatewaypundit.com/2012/09/flashback-gallup-had-carter-up-4-points-over-ronald-reagan-in-september-1980/carter-reagan/

itsspideyman on September 25, 2012 at 1:12 PM

..actually it’s worse than garbage because it exacerbates the skew by putting the results of polls with sound internals on the same footing of those with flawed internals by merely averaging the two results. For example, a poll of the Chicago office of OFA and a poll of 3,000 likely voters in Oiho are not the same and the average results are wa-a-a-a-a-y skewed.

The War Planner on September 25, 2012 at 12:40 PM

Good point. It’s a way for them to re-cast the accurate poll as the flyer / outlier and essentially remove it from consideration by burying it with garbage polls.

rayra on September 25, 2012 at 1:13 PM

Between THIS and Obama talking about the FUTURE not belonging to those that “slander” Islam…….

Madonna offered a profanity-laced endorsement of President Obama at her concert Monday night, which involved the singer stripping down to her underwear to reveal the president’s name written on her body.

“You all better vote for f—ing Obama okay,” she told the crowd at Washington D.C.’s Verizon Center.

Later in the show, Madonna took off her shirt and pulled down her pants to show she had “OBAMA” written in all capital letters across her lower back.

“When Obama is in the White House for a second term I’ll take it all off,” she said to cheers and whistles from the audience.

PappyD61 on September 25, 2012 at 1:15 PM

“Vote for our icky moderate nominee or the universe will implode!!!!” Some people are tired to death of THAT as well.

ddumbo

They’re called Obama voters.

xblade on September 25, 2012 at 1:18 PM

“I am shocked! Shocked to discover that polling firms in the service of Democratic clients are falsifying their results to please their clients!”

Why are these pollsters SO DEFENSIVE?

Maybe its because they know if the SCOAMF is defeated … they will ALL be out of a job ?!?

PolAgnostic on September 25, 2012 at 1:19 PM

This is absolutely huge news. The dumb voter crowd listens to Madonna. Some of them will undoubtably have a double take? Huh? You mean I’m voting for the Muslim guy.

There’s a lot of them that are going do change their minds over this.

Even gays are going to wonder, aren’t the Muslims the ones who are hanging homosexuals from lampposts in Baghdad and Tehran?

Certainly the rock ‘n roll drug legalizing crowd is not going to be thrilled with the thought of voting for a free speech banning Muslim.

ericdondero on September 25, 2012 at 1:20 PM

Hey gumbyandpokey,

does the Obama campaign just assign you to HOT AIR or are you responsible for more conservative websites.

Just wondering.

lol

gerrym51 on September 25, 2012 at 1:21 PM

This is absolutely huge news. The dumb voter crowd listens to Madonna. Some of them will undoubtably have a double take? Huh? You mean I’m voting for the Muslim guy.
ericdondero on September 25, 2012 at 1:20 PM

There’s a whole lotta sarcastic “Gee, thanks for helping, Madonna” Dem comments at HuffPo. heheheh.

whatcat on September 25, 2012 at 1:31 PM

ericdondero on September 25, 2012 at 1:20 PM

There’s a whole lotta sarcastic “Gee, thanks for helping, Madonna” Dem comments at HuffPo. heheheh.

whatcat on September 25, 2012 at 1:31 PM

And she wasn’t being sarcastic. The whole rant here.

de rigueur on September 25, 2012 at 1:51 PM

ddrintin is a shill who wants Obama to win — a troll — a democrat sent there to upset folks — he’s eminently ignorable — so ignore him — the more you respond the move his ilk gets into the thread — just ignore him and he may go away — but he’s so egotistical it may take some time.

rebuzz on September 25, 2012 at 10:55 AM

No, a supremely butthurt Palinista (disclaimer: I am a Palinista too) who never got over it and decided to take it out on everyone else.

Most Palinistas are adults. ddrintin thinks that he/she is going to show the rest of us by engaging in hamster wheel discussions here until the election and then either staying home or voting Obama.

ddrintin has not figured out that not only will we suffer for his/her foolishness, but also everyone that he/she loves and is a friend of.

*shrug*

Not much you can do with that kind of spitefulness.

kim roy on September 25, 2012 at 2:18 PM

NO! We are not too sensitive to those stinky,slimy,lying,democratic skewing pollsters.

gerrym51 on September 25, 2012 at 2:18 PM

gumbyandpokey on September 25, 2012 at 1:03 PM

your choices.

Obama
Romney
Johnson
don’t vote
move to Canada

gerrym51 on September 25, 2012 at 2:19 PM

Comment pages: 1 2 3