WaPo/ABC ends sample transparency in national polling

posted at 9:50 am on February 6, 2012 by Ed Morrissey

The Washington Post and ABC News has a new national poll out today.  It purports to show that Barack Obama has a 50% approval rating and that he would beat Mitt Romney in a head-to-head matchup.  And heck, that might even be true, except for a couple of problems.  First, this is a poll of general population adults rather than registered or likely voters, so it’s not even a proper polling type for the predictive outcome they claim.

More importantly, though, the poll series has dropped its reporting of partisan identification within their samples.  It’s the second time that the poll has not included the D/R/I split in its sample report, and now it looks as though this will be policy from this point forward.  Since this is a poll series that has handed double-digit partisan advantages to Democrats in the past (for instance, this poll from April 2011 where the sample only had 22% Republicans), it’s not enough to just hear “trust us” on sample integrity from the Washington Post or ABC.

One cannot determine whether Obama’s improvement in this series is a result of the State of the Union speech, as Dan Balz and Jon Cohen suggest, or whether it’s due to shifting the sample to favor Democrats more so than in previous samples.  The same is true for the Post’s report that Obama “for the first time has a clear edge” over Romney head-to-head.  One would need a poll of registered or likely voters to actually make that claim (one has to register to cast a vote, after all), and one would need to see the difference in partisan splits between this and other surveys in the series to determine whether the movement actually exists or got manufactured by the pollster.

Essentially, the overall poll is worthless, and given the track record of this poll series, it’s easy to assume that the reason that the Post has ended its sample transparency is because they have something to hide.

Among the Republicans and independents the Post did survey, Romney has a big lead over the rest of the field, 39/23 over Gingrich, with Santorum coming in at 16% and Paul at 15%.  Since we don’t know the mix between Republicans and independents here, either, and we’re still dealing with adults in the middle of the primaries when the likely voter model should be used, this is also a worthless result.

Update: The description in their news reports show 879 registered voters as a subsample.  However, their sample report only mentions the 1,000 adults of the overall sample, from which Obama’s 50% approval rating is taken, as well as their approval rating for the GOP rhetoric, which is prominently mentioned in the news report.  They do, however, report on both general population and registered voters for the Obama-Romney head-to-head — but again without any indication of the sample composition at all.

And once again, why anyone is polling adults in the middle of an ongoing primary is a complete mystery.  That should be likely voters.


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

The point of these polls is that it allows the Journolisters to all start writing their “Obama is the new Comeback Kid!!!1!1!!!!” stories, which they are all dying to write. The Post timed this one very carfully to coincide with the first glimmer of decent economic news. This morning CNBC was all about the “auto industry comeback” and how much this helps Obama since all the Republicans opposed the GM/Chrysler bailouts.

All it takes is one deliberately skewed poll to start the avalanche of comeback stories. Still doesn’t mean Obama is more electable now than he was a week ago, it is more for the journalistas’ benefit than anything.

rockmom on February 6, 2012 at 10:52 AM

Why would anyone expect more than Mickey Mouse polling from Disney TV?

EconomicNeocon on February 6, 2012 at 10:52 AM

They can’t adjust them by partisan split because that is not a static variable, so they don’t.

But they used to provide the splits they used in each poll. They’re no longer doing that. Why?

Missy on February 6, 2012 at 10:53 AM

cozmo on February 6, 2012 at 10:50 AM

Hahahahaha. One defense of Romney does not a habit make you tool.

csdeven on February 6, 2012 at 10:53 AM

rockmom on February 6, 2012 at 10:52 AM

Precisely. It is all about narrative construction.

Missy on February 6, 2012 at 10:54 AM

Shaun Cassidy? Donny Osmond?

lisa fox on February 6, 2012 at 10:55 AM

Are they attempting to suppress GOP and Independent voter turnout by lying to everyone?

That, and convincing people who can’t make a decision on their own to vote for Giggles because he’s already garenteed to win. Sheeple will back a winner even if it’s against their own self-interests.

crazy_legs on February 6, 2012 at 10:55 AM

WaPo has in the past been busted for over-sampling Democrats by 14% or more (I even saw one where they oversampled Dems by 19%) and AP has run a couple of “polls” where they actually sampled twice as many Democrats as Republicans to get the result they desired.

Del Dolemonte on February 6, 2012 at 10:48 AM

WaPo has been oversampling Dems for decades. It’s always been a worthless poll and now is even more so.

Missy on February 6, 2012 at 10:56 AM

Ed,

You’re missing the biggest flaw in this poll. There is no initial ballot at the beginning of questioning that asks “who would you vote for Obama or Romney?” That is always asked as qualifier BEFORE messaging.

They only ask that question AFTER influencing questions, such as Romney’s wealth, religious faith, and tax structure are asked. THAT is why this poll is junk. I don’t want to say this is “pushing” respondents in a certain direction, but it’s pretty worthless nonetheless.

Butters on February 6, 2012 at 10:57 AM

They’re trying to hide the real poll numbers, which are likely very bad for Obama.

RebeccaH on February 6, 2012 at 10:58 AM

Do lefties go bat**** nuts,too, and attack polls when they don’t like the results?

gumbyandpokey on February 6, 2012 at 10:40 AM

Where were you in November of 2004? The Exit Polls showed Thurston Howell the 3rd beating Chimpy Bush, so much so that the Left called the faulty exit polling “a conspiracy”.

It is important to remember how large the discrepancy was between the early vote tallies and the early exit poll figures. By the time polls were closing in the eastern states, the vote-count figures published by CNN showed Bush leading Kerry by a massive 11 percent margin. At 8:50 p.m. EST, Bush was credited with 6,590,476 votes, and Kerry with 5,239,414. This margin gradually shrank. By 9:00 p.m., Bush purportedly had 8,284,599 votes, and Kerry 6,703,874; by 9:06 p.m., Bush had 9,257,135, and Kerry had 7,652,510, giving the incumbent a 9 percent lead, with 54 percent of the vote to Kerry’s 45 percent.

At the same time, embarrassingly enough, the national exit poll figures reported by CNN showed Kerry as holding a narrow but potentially decisive lead over Bush. At 9:06 p.m. EST, the exit polls indicated that women’s votes (54 percent of the total) were going 54 percent to Kerry, 45 percent to Bush, and 1 percent to Nader; men’s votes (46 percent of the total) were breaking 51 percent to Bush, 47 percent to Kerry, and 1 percent to Nader. Kerry, in other words, was leading Bush by nearly 3 percent.

The early exit polls appear to have caused some concern to the good people at the National Election Pool: a gap of 12 or 14 percent between tallied results and exit polls can hardly inspire confidence in the legitimacy of an election.

One can surmise that instructions of two sorts were issued. The election-massagers working for Diebold, ES&S (Election Systems & Software) and the other suppliers of black-box voting machines may have been told to go easy on their manipulations of back-door ‘Democrat-Delete’ software: mere victory was what the Bush campaign wanted, not an implausible landslide. And the number crunchers at the National Election Pool may have been asked to fix up those awkward exit polls.

Fix them they did. When the national exit polls were last updated, at 1:36 a.m. EST on November 3, men’s votes (still 46 percent of the total) had gone 54 percent to Bush, 45 percent to Kerry, and 1 percent to Nader; women’s votes (54 percent of the total) had gone 47 percent to Bush, 52 percent to Kerry, and 1 percent to Nader.

Del Dolemonte on February 6, 2012 at 10:58 AM

cozmo on February 6, 2012 at 10:50 AM

Hahahahaha. One defense of Romney does not a habit make you tool.

csdeven on February 6, 2012 at 10:53 AM

I would say you finally went over the bend, but you did that long ago.

Since anyone who defends Romney would be considered an ally of yours, why would anybody want to.

cozmo on February 6, 2012 at 11:00 AM

From an article by Nate Silver on how badly Rasmussen polls performed in the midterms:

Rasmussen also weights their surveys based on preordained assumptions about the party identification of voters in each state, a relatively unusual practice that many polling firms consider dubious since party identification (unlike characteristics like age and gender) is often quite fluid.

Apparently WaPO/ABC also hold that view. It’s supposed to be a random sample, you can’t just throw out data that doesn’t fit your preconceptions about the electorate. Only half-joking, but I think the real bias is that a lot of people are embarrassed to self-identify as Republicans over the phone.

Also, this far out from the election, “likely voters” probably doesn’t mean a whole lot.

RightOFLeft on February 6, 2012 at 11:01 AM

I have it on good authority that the “sample composition” was a mix of occupants in the 5 major voting precincts of Chicago.

1. Montrose Cemetery
2. Graceland Cemetery
3. Rosehill Cemetery
4. Oak Woods Cemetery
5. Bohemian National Cemetery

Oh, a number of the occupants were polled more than once.

Crimefyter on February 6, 2012 at 11:03 AM

If enough of this polling nonsense is exposed, and expounded on, we may finally see an end to government by instant poll. The use of polling as a “governing” tool, let alone a campaigning benchmark, is one of the reasons why this country is in the difficulties that it is in.

Scriptor on February 6, 2012 at 11:03 AM

Romney won all these primaries and caucuses because of money.

He will be coming up against 1 billion dollars.

liberal4life on February 6, 2012 at 11:04 AM

The WashPo has turned into a high school newspaper.

NoDonkey on February 6, 2012 at 9:54 AM

Comedy gold.

DevilsPrinciple on February 6, 2012 at 11:05 AM

Very good catch, Ed. No reason to give any credence to non-transparent polls. I could take one of those right now and tell you Americans prefer Rick Perry over Obama 65 to 35.

J.E. Dyer on February 6, 2012 at 11:05 AM

Romney won all these primaries and caucuses because of money.

He will be coming up against 1 billion dollars.

liberal4life on February 6, 2012 at 11:04 AM

And Mr. Biggelsworth. Don’t want to forget about him.

Kataklysmic on February 6, 2012 at 11:10 AM

Del Dolemonte on February 6, 2012 at 10:58 AM

I well remember this. One of the dumbest arguments of all time. The early exit poll results were leaked in the middle of the day. Anyone who had yet to vote obviously wasn’t polled. The sample was thus totally unrepresentative, hence the imbalance. But that didn’t stop the morons from conspiracy-mongering.

If anything the leak was an attempt by Dems and the MSM to influence ongoing voting – “hey Bush voters, don’t bother going to the polls, Kerry has it in the bag.”

Missy on February 6, 2012 at 11:11 AM

One Word: Propaganda

nofreelunch on February 6, 2012 at 11:12 AM

The left must feel like they have secured power. Things are going to get ugly fast.

tom daschle concerned on February 6, 2012 at 11:15 AM

I thought the following post belonged here; it’s long, but it’s something I read just this weekend on Big Government, typos and all. The commenter who posted it saved it from 2008, and as you can see, it appears the MSM is using the same playbook. I’m a firm believer in opposition research and learning from the enemy to use their tactics against them; it’s also helpful to know that there are some people out there who are tired of the lying and who seem to want to be truthful. Finally, this is very educational and confirms my (and many others, I’m sure) suspicions that virtually everything surrounding a political campaign is never what it seems. Read, learn and enjoy.

(this was save from 2008… off a blog at fox news)

A confession of Democrat campaign worker in 2008 –
“Ok, I want to clear my conscious a little. Hopefully you could make a blog post to help some fellow clinton supporters out. I work for a campaign and can’t wait for this week to be over. I was doing it for a job. I was not a fan of any candidate but over time grew to love HRC.(Hillery R. Clinton) The internal campaign idea is to twist, distort, humiliate and finally dispirit you.

Continued Part 2

“A confession of Democrat campaign worker in 2008″

We pay people and organize people to go to all the online sites and “play the part of a clinton or mccain supporter who just switched our support for obama” We do this to stifle your motivation and to destroy your confidence. We did this the whole primary and it worked. Sprinkle in mass vote confusion and it becomes bewildering. Most people lose patience and just give up on their support of a candidate and decide to just block out tv, news, websites, etc. This surprisingly has had a huge suppressing movement and vote turnout issues. Next, we infiltrate all the blogs and all the youtube videos and overwhelm the voting, the comments, etc. All to continue this appearance of overwhelming world support. People makes posts to the effect that the world has “gone mad”
Thats the intention. To make you feel stressed and crazy and feel like the world is ending.

We have also had quite a hand in skewing many many polls, some we couldn’t control as much as we would have liked. But many we have spoiled over. Just enough to make real clear politics look scarey to a mccain supporter. Its worked, alough the goal was to appear 13-15 points ahead. The polls are roughly 3-5 points in favor of Barack. Thats due to our inflation of the polls and pulling in the sheeple. See, the results have been working. People tend to support a winner, go with the flow, become “sheeple” The internal campaign idea is to twist, distort, humiliate and finally dispirit you. Our donors, are the same people who finance the MSM. Their interests are tied, Barack then tends to come across as teflon. Nothing sticks. And trust, there were meetings with Fox news. The goal was to blunt them as much as possible. Watch Bill Oreilly he has become much more diplomatic and “fair and balanced” and soft. Its because he wants to retain the #1 spot on cable news and to do that he has to have access to the Obama campaign and we worked hard at stringing him a long and keeping him soft for an interview swap. It worked and now he is anticipating more access. So he is playing it still soft. This is why nothing sticks. The operation is massive, the goal is to paint a picture that is that of a winner, regardless of the results.

Continued pt 3
Confession of Democrat Campaign worker 2008

There is no true inauguration draft or true grant park construction going on. There will be a party, but we are boasting beyond the truth to make it seem like the election is wrapped up. Our goal is to continue to make you lose your morale. We worked hard at persuasion and paying off and timing and playing the right political numbers to get key republican endorsements to make it seem even more like it was over and the world was coming to an end for you all. There is a huge staff of people working around the clock, watching every site, blogs, etc. We flood these sites. We have had a goal to overwhelm. The truth is here. I could go on and on, but you get the picture. I am saying this because I know HRC was better for the country, and now realize this. I was too late by the time I connected to her. To me Barack was just a cool young dude that seemed like a star. I didn’t know him or his policies, but now I understand more than I care to and I realize his interests are more for him, and the DNC and all working like puppets with dean. I always thought a president wanted the better good for the country. The end result I see is everyone dependent on the government, this means more and more people voting for the DNC. This means the future is forever altered. I don’t see this as america, so I am now supporting John Mccain. Sarah Palin is a huge threat, and our campaign has feared her like you can’t imagine. If it seems unfair how she has been treated, well its because she has had a team working round the clock to make her look like a fool. this is a big conspiracy and I am so shocked that its not realized. We released a little blurb the other day that the Obama campaign was already working on reelection and now putting our efforts towards 2012. This was to make it seem like it was above us to continue caring about 2008. Trust me, its a lie. David is very smart, but its a sticky ugly not very truthful kind of intelligence. Its not over yet, but I think the machine is working. And its a hill to climb. I will be quitting my post on nov 5th and my vote will be for John Mccain. Fortunately, my position has been a marketing position and I don’t feel I had any part of anything I would feel guilty for. But I look forward to getting out of this as the negativity and environment upsets me. I wish you all well, and goodluck. I understand your plight ”

PatriotGal2257 on February 6, 2012 at 11:16 AM

Obama cannot run on his record so he will attack his opponent.

Romney cannot run on his record so he attacks Newt.

If Romney is the nominee, he will be attacked with a billion dollars and the MSM. Romney will fold like he did on the Fox interview. It is not going to be pretty.

Kaffa on February 6, 2012 at 11:18 AM

Here’s the original article where the comment was posted.

Political Moneyball: The Conservative Strategy for Winning the Fight Coming After the Election

PatriotGal2257 on February 6, 2012 at 11:21 AM

Apparently WaPO/ABC also hold that view.

I don’t think you can conclude that. WaPo used to provide the party ID splits they used to weight results (which would change over time). Now they are no longer providing those splits. But they haven’t said they are no longer weighting to party ID.

Missy on February 6, 2012 at 11:21 AM

When my oldest boy went to Iraq as a Navy Corpsman I told him two things: Obey your commanding officer and never leave the wire with anyone from the American press corps.
The Marines in his company, to a man, agreed with this. Their non-coms and C.O. made it clear to the powers that be that the men did not trust the U.S. press and would not cooperate with them.
There is a clip of Dan Rather or Tom Brokaw in Viet Nam being asked If they knew of an upcoming ambush against American troops would they tell them. No was the answer.
The American media should be confronted at every turn. On the streets, in restaurants, anywhere you see them. These liberal frauds need to know we are on to them. When they promote their agenda in schools they should be taken on at PTA meetings. The days of being nice are over.

Thicklugdonkey on February 6, 2012 at 11:28 AM

All they need to do is fool the idiots in the middle who will be watching American Idol and Dancing with the Stars up until election day and then will walk into a voting booth and saying “OK, who do I FEEL like voting for? Who are all the cool kids voting for?” You don’t persuade people like that with logic. In that regard the dems run circles around the republicans.

xrayiiis on February 6, 2012 at 11:31 AM

NewsBusters: ‘Does Axelrod Poll For ABC?’
http://newsbusters.org/blogs/mark-finkelstein/2012/02/06/does-axelrod-poll-abc

StewartIII on February 6, 2012 at 11:32 AM

1.2 million Republican voters in the past poll, no longer exist in this time and space dimension.

Hey, Washington Post readers/ABC news viewers are dumb enough to lap it up, why not.

MNHawk on February 6, 2012 at 11:36 AM

Both WaPo and ABC are listed as members of the AAPOR Transperancy Initiative, a professional effort to instill confidence in polling organizations statements, but the central tenant of the effort is to reveal the important components of methodology at tehtime the poll itself is released.

This is a clear violation of what the organization itself has defined as “ethical behavior” for polling organizations. You are right to assume the results may well be nothing more than propaganda, at least that’s what the polling industry would say.

MTF on February 6, 2012 at 11:41 AM

Or as Sarah Palin has famously said, “they make stuff up”.

Apparently the MSM polling has come to this.

PatriotGal, thanks for reposting that. I believe it was transparent that effort was underway, and still is. The trolls all post the same talking points. Same with the talking MSM heads. Rush often strings the soundbites together and those morons all just keep saying the exact same phrase.

karenhasfreedom on February 6, 2012 at 11:44 AM

Between now and November every bit of positive news will be attributed to Obama. Every “improving” statistic on the economy and employment will be suspect at best, and every such rosy projection will be also. Obama has never accepted responsibility for a negative outcome, and he isn’t about to start. He has already indicated his puerile campaign strategy, and the leftist media have lined up behind it, little puppy-dog tails wagging delightedly. “Ugly” won’t begin to describe the next 6-8 months. “Disgusting” is a good place to start, and expect decline from there.

OzzieMan on February 6, 2012 at 11:47 AM

Note to Ed:

I think the source of this polling decision is that that the democrats have stated a strategy that depends on the turnout model from 2008. This group that provided the cushion for Obama are the kind of voters who won’t turnout unless motivated by something.

These voters are the kind that get lazy when they don’t think they are voting for a winner. Axelrod has already stated a theory like this in the past. He used inevitability to get past Hillary and McCain in 2008 with these voters.

What that means is Obama cannot be a marked loser in the polls without effecting the exact voters they need to turnout so the MSM like ABC/Post will what they have to tell these voters they are onboard with a winner still.

It isn’t the way conservatives think but it is the way the drone voters on the left think. They don’t show up unless they think they get a check out of it. Don’t doubt what that one woman in 2008 said when she said “I won’t have to worry about gas in my tank anymore”. She won’t show up if Obama is polling bad.

Conan on February 6, 2012 at 11:48 AM

Their motto is unspoken, but very clear: We have no shame.

Ken James on February 6, 2012 at 11:49 AM

And once again, why anyone is polling adults in the middle of an ongoing primary is a complete mystery. That should be likely voters.

Complete mystery, Ed? Really? I think you know why they’re doing this.

BKeyser on February 6, 2012 at 11:51 AM

Look for more crap polls like this from the MSM. I strongly suspect they’re being made up out of whole cloth with numbers being pulled out of someone’s liberal ass.

GarandFan on February 6, 2012 at 11:51 AM

My lord, I am truly sickened by the commenting going on at the WaPo boards about this poll. Most of the commenters are certifiably INSANE.

NOMOBO on February 6, 2012 at 11:53 AM

And yes, most pollsters do weight for Party ID. We’ve seen it here in the past, especially with WaPo and al-AP “polls”.

WaPo has in the past been busted for over-sampling Democrats by 14% or more (I even saw one where they oversampled Dems by 19%) and AP has run a couple of “polls” where they actually sampled twice as many Democrats as Republicans to get the result they desired.

Del Dolemonte on February 6, 2012 at 10:48 AM

Completely false. Most pollsters don’t weight for party ID – basically nobody does it – which is generally regarded as a dubious practice.

I think that you don’t even know what weighting for party ID means, considering your second paragraph.

Again: 1) I wouldn’t pay much attention to what Ed Morrissey has to say about polls 2) what this poll and others show is that this primary needs to end quickly

joana on February 6, 2012 at 11:57 AM

Again: 1) I wouldn’t pay much attention to what Ed Morrissey has to say about polls 2) what this poll and others show is that this primary needs to end quickly

joana on February 6, 2012 at 11:57 AM

Thanks, but I’ll take the capn’s poll analysis over yours any day.

cozmo on February 6, 2012 at 11:59 AM

I remember when I read polls which said Obama was going to win and win comfortably against McCain. Most people here criticized Gallup for being bias blah blah blah. We all know what happened.

liberal4life on February 6, 2012 at 11:59 AM

Did WaPo reveal the breakdown the percentage of Republicans, Independents, and Democrats that prefer Obama or Romney? If so, the sample composition could be “backed out” by solving three equations in three unknowns.

Steve Z on February 6, 2012 at 12:02 PM

Rasmussen has Obama up 7. Even a worse result for the GOP than this WAPO poll. Are we going to blame the pollster too?

Republicans have been beating up each other in the most nasty ways for months. This needs to stop.

joana on February 6, 2012 at 12:02 PM

Romney won all these primaries and caucuses because of money.

He will be coming up against 1 billion dollars.

liberal4life on February 6, 2012 at 11:04 AM

I thought that was an urban legend? At least that’s what O’bama campaign manager Jim Messina said a few months ago.

In fact, he called the claim ”bullsh**”

Del Dolemonte on February 6, 2012 at 12:03 PM

Thanks, but I’ll take the capn’s poll analysis over yours any day.

cozmo on February 6, 2012 at 11:59 AM

It’s your prerogative.

However, it’s a fact that weighting for party ID is regarded as a malpractice by most pollsters and that his rant about wanting a poll of likely voters is pure ignorance – it doesn’t make sense to poll likely voters 8 months away from the elections, regardless if it’s primary season or not.

Nobody – certainly not Ed – will counter-argue these points simply because there aren’t any good counter-arguments to be made.

joana on February 6, 2012 at 12:05 PM

And once again, why anyone is polling adults in the middle of an ongoing primary is a complete mystery.

No mystery. When reality is against them they simply alter the reality. Hallucinogens and intellectual dishonesty have always served the Left well in these situations.

cicerone on February 6, 2012 at 12:07 PM

And once again, why anyone is polling adults in the middle of an ongoing primary is a complete mystery.

Come on, Ed. We’re talking about the left-wing mainstream media. You know, the same left-wing mainstream media that had Obama’s back during the 2008 primaries and general by not reporting on anything in his past. Now it’s 2012 and they’ve got his back again in that they are acting as the public relations and media arm of his presidential reelection campaign. Why they are polling adults rather than likely voters in the middle of an ongoing primary is no mystery at all.

Kim Priestap on February 6, 2012 at 12:07 PM

So, there is no one out there, that can do polls that represent things we actually want to know?

MSM push polls, I guess one option is to hang up the phone totally, or answer the opposite of how they are baiting you to.

YES I love Mitch McConnell, he is doing a superior job.

No, I don’t recognize the name Obama on that list.

The House has passed 30 bills, I give 100% approval for the House of Representatives.

and see what happens….

Fleuries on February 6, 2012 at 12:14 PM

I think that you don’t even know what weighting for party ID means, considering your second paragraph.

joana on February 6, 2012 at 11:57 AM

Oh please, Dear, I have taken plenty of university-level statistics courses and use statistics methodology in my business daily.

I’ve also been following these “polls” for well over 25 years. I’ve seen all the “methodology” the pollsters use, and know the difference between weighted and unweighted samples related to Party ID.

When they deem to disclose the info at all, the Democrat Media sources like the WaPo always bury the poll sample on the very last page of the PDF they include with the poll. That’s because they know that the average “reader” is too lazy to go that far to see what the methodology actually was.

Back in December of 2011 (December 12-15 to be exact), the WaPo did a “poll” that showed O’bama’s “job approval” to be:

Approve 49%
Disapprove 47%

Their poll sample:

Democrats 32%
Republicans 25%

Yet just a month earlier, the very same WaPo did the exact same “poll”, and got these results:

Approve 44%
Disapprove 53%

Their poll sample:

Democrats 29%
Republicans 26%

See what a difference cooking the numbers can make?

Del Dolemonte on February 6, 2012 at 12:20 PM

MiniTru has arrived just 30 years late. This is laying the groundwork for the inner cities burning on election night.

jukin3 on February 6, 2012 at 12:21 PM

However, it’s a fact that weighting for party ID is regarded as a malpractice by most pollsters

joana on February 6, 2012 at 12:05 PM

Leftist Poll Cruncher Nate Silver, circa 2006:

Responsible pollsters should always disclose the partisan ID composition of their samples, and should notate in their press releases when material shifts occur. Regardless of the above, there is little doubt that the partisan ID composition of a poll is an extremely important element in the proper interpretation of a poll. Pollsters should always report the partisan ID composition of their sample, and should qualify in their write-ups when substantial changes in party ID have occurred since their last survey.

–Nate Silver

The above cite came from Nate’s article in the Leftist New Republic.

Nate was in fact in this article complaining about pollsters oversampling Republicans, to make Bush look good!

Del Dolemonte on February 6, 2012 at 12:32 PM

And once again, why anyone is polling adults in the middle of an ongoing primary is a complete mystery. That should be likely voters.

Call me cynical, but there is no mystery about the reason they are doing it this way at all.

AUINSC on February 6, 2012 at 12:35 PM

However, it’s a fact that weighting for party ID is regarded as a malpractice by most pollsters and that his rant about wanting a poll of likely voters is pure ignorance – it doesn’t make sense to poll likely voters 8 months away from the elections, regardless if it’s primary season or not.

Nobody – certainly not Ed – will counter-argue these points simply because there aren’t any good counter-arguments to be made.

joana on February 6, 2012 at 12:05 PM

Wrong, wrong and wrong.

WaPo and ABC are violating their own promises to make a “basic disclosures of methods and data” in reporting these “poll results”. It has nothing to do with weighting, with the actual results or who was polled.

The organizations are violating industry practices for transparency that they have assured us they would abide by. That’s all that matters and, if anything, Ed’s criticisms are too mild.

MTF on February 6, 2012 at 12:35 PM

Begin with a conclusion and manufacture evidence to support it.

Grunt on February 6, 2012 at 12:40 PM

joana: They may not be reweighting the sample for party affiliation, but that does not make the sample valid.

Without knowing how the party affiliations voted, we cannot reweight.

Even without all of this, if the sample is 40% Democrat, 25% Republican, and 35% ‘Independent’, with this result, do you think that is representative of the electorate in this country?

This could be exactly what it is purported to be. By that, I mean that this poll has not been doctored in any way (other than the question order, which by itself is enough to throw it out). Even if the poll results have not been doctored, that does not mean it is representative, and due to the fact that we are not given the descriptive statistics, we cannot verify it.

I do like, though, you use it to argue for an end you prefer. In that, you are no different from anyone else using a poll for a political end.

Scott H on February 6, 2012 at 12:41 PM

Leftist Noam Chomsky coined the term “manufacturing consent.” Polls from media outlets must be presumed to be leftwing/Obama propaganda.

georgej on February 6, 2012 at 12:48 PM

You wrong WaPo/ABC: far from abandoning transparency, they’re implementing the New Transparency pioneered by the Obama administration.

PersonFromPorlock on February 6, 2012 at 12:51 PM

What a very curious time for the WaPo and ABC to be dropping party identification from their polls…right during presidential election season.

OxyCon on February 6, 2012 at 12:54 PM

PatriotGal2257

Brilliant post.

It should be reposted in every thread.

The Romney machine is on full blast even (most likely especially) here at HA.

If conservatives are able to solidify he’s in for a terrible fight (if not finished).

sublibertate on February 6, 2012 at 12:59 PM

He will be coming up against 1 billion dollars.

liberal4life on February 6, 2012 at 11:04 AM

Of course Obama can’t raise a billion through normal fund raising channels, so he’ll use the “campaign donation” money from Solyndra and Ener1. It definitely gives new meaning to “green start-ups”

DevilsPrinciple on February 6, 2012 at 1:08 PM

karenhasfreedom on February 6, 2012 at 11:44 AM

You’re quite welcome. I get a kick out of hearing Rush string together bunches of audio clips of MSM talking heads all saying variations of the same thing. You’d think they’d want to change it up a little bit so as not to sound like a carbon copy, but we all know they’re not that smart. :)

The American media should be confronted at every turn. On the streets, in restaurants, anywhere you see them. These liberal frauds need to know we are on to them. When they promote their agenda in schools they should be taken on at PTA meetings. The days of being nice are over.

Thicklugdonkey on February 6, 2012 at 11:28 AM

THIS. ^^^^^^^^

Yes, the days of being nice are over.

PatriotGal2257 on February 6, 2012 at 1:08 PM

Like Mark Twain said,”Figures lie and Liars Figure”.

Rosemary Kelly on February 6, 2012 at 1:09 PM

Trnslation: ABC doesn’t want the public to know that they skew their polls to provide the outcomes they desire.

lukjuj on February 6, 2012 at 1:21 PM

sublibertate on February 6, 2012 at 12:59 PM

Thanks. As soon as I read it, I thought the same thing about posting it everywhere. I didn’t realize I’d get to do it so soon. :)

Please feel free to copy and post as many places as possible yourself. Whoever that was in 2008 has done a massive public service, as did the person who copied it.

PatriotGal2257 on February 6, 2012 at 1:27 PM

Another Leftist Liars Propaganda Poll….

It has been proved repeatedly that Rasmussen polls are among the MOST ACCURATE of all. Unlike the lunatic-left fake polls conduced by Washington Post, NYT, abc news, cbs, and the other lamestreamers, Rasmussen does an honest, real-life sampling – not a skewed mixed designed to favor the d-cRAT socialists by INCREASING the percentage of blacks and other lunatic-left leaning groups (as PPP, GfK/AP and the Washington Post, in particular, do) or INCREASING the sampling in blue-states and cities (as the NYT and A(lways)B(iased-socialist)C(lowns), in particular do), or inflating the percentage of d-cRAT socialists in the sample (as ALL of the leftist pollsters/propagandists/LIARS do).

Believe Rasmussen – ignore the others.

TeaPartyNation on February 6, 2012 at 1:28 PM

The BHO wannabes, WaPo and the All Barack Channel, are just practicing Obama transparency.

stukinIL4now on February 6, 2012 at 1:36 PM

What do you expect from a Washington Propaganda/AllBullCrap poll.

galtani on February 6, 2012 at 1:37 PM

PatriotGal2257 on February 6, 2012 at 11:16 AM

Interesting. And it explains fools such as cd seven to a ‘T’.

Lanceman on February 6, 2012 at 2:11 PM

Your opinion, My opinion, Your Money, My Money..

Maybe it is a “spiritual embodiment” of the fairness doctrine.

You know, it is everyone’s expression of opinion not the relevance to reality which matter. Everyone has a piece of a cosmic opinion.

I thinking of conducting a seminar in New York on this. It will begin with Hegel’s synthesis of consciousness and come forward to the Occupy Wall Street zeitgeist.

I have a second seminar coming in explaining why AARP keeps bring up imaginary attacks on medicare. NO Republican or Bill O’Reilly understand that maneuver or a few other things I have heard about.

Poor, innocent children with their balanced budgets, Lincoln books and Kirsten Powers. Well, KP has been so much better lately and she seems to be getting some sleep. She can’t carry water for Ms. Perino let alone run with Dr. K yet — but it is nice to hear her now.

IlikedAUH2O on February 6, 2012 at 2:16 PM

This is just the start.

If government organs like the WaPo were being honest, then we’d know one of two things:

a) The editorial consensus was that Obama and Democrats were secure, or

b) They knew the game was up, that no matter what they did the voters were reaching for the flush lever and Obama soon would be swirling the bowl of history.

This latter is recognizable as the fifth stage of grief, and they’d have to work their way through the other four first.

So if things continue to look bad for The One, we can expect a lot of wacky crap to come out of the media. Come early October you probably wouldn’t want to be walking the streets under any NY Times office windows.

JEM on February 6, 2012 at 2:18 PM

I just completed my own poll and like ABC, I’m not sharing who I polled.
Results: 100% of respondents think Obama would lose in a general election to a mushroom growing on a pile of Horse Dung. I did however use only a registered voter.

buckeyerich on February 6, 2012 at 2:36 PM

Wow, it’s even worse than we thiought, folks. From The Hill:

The Mitt Romney campaign fired back at what they called “seriously flawed” polling data in Monday’s Washington Post/ABC News poll.

The poll shows President Obama opening up a nine-point lead against the GOP front-runner among voters nationally, and holding a 12-point lead among independents.

Romney spokeswoman Gail Gitcho said in a statement that the poll introduced “specific negative information about Governor Romney immediately prior to asking the ballot match-up against President Obama.”

“Immediately prior to the President ballot test, this poll introduced information regarding Romney’s background and suggested ‘he cut jobs,’ ‘he benefited from opportunities that are not available to other people,’ ‘he is not paying his fair share of taxes’ and that his Mormon religion might be a factor not to support him,” Gitcho said.

“Their Presidential ballot test is pretty clearly tainted by the questions asked immediately prior to the ballot, resulting in what some would call a ‘pushed’ ballot. A pollster can’t ask or suggest specific negatives on a candidate immediately prior to a ballot test and expect to get anything other than a biased result.”

In the poll, questions 28 through 31 surveyed voter reactions to some of the criticisms Romney’s rivals have lodged against the former Massachusetts governor, such as whether he is paying his fair share of taxes, while question 32 is the head-to-head match-up question between Romney and Obama, which generated the headline “Obama holds edge over Romney” in the Washington Post story.

“Survey design is complicated,” Gitcho concluded. “But this is one of those times when a mistake was made and should not be repeated in the future.”
—-

Now you know how they do it.

rockmom on February 6, 2012 at 3:34 PM

WaPo has pretty well abandoned any pretense of objectivity and become a Democratic house organ. Their circulation and revenue are following the same path of most newspapers, a long downward spiral.

Eventually when Dan Balz is panhandling on the street, toss him a coin.

Adjoran on February 6, 2012 at 3:40 PM

Hiding the truth is “big business” reaping huge cash rewards. Good luck in even slowing that down since there is way too much cash and personal property to steal from the gullible, self destructive, and suicidal masses that continue to vote Marxist Democrats and Republicans into office.

aposematic on February 6, 2012 at 3:45 PM

I don’t think you can conclude that. WaPo used to provide the party ID splits they used to weight results (which would change over time). Now they are no longer providing those splits. But they haven’t said they are no longer weighting to party ID.

Missy on February 6, 2012 at 11:21 AM

I might have the wrong idea of what it means to weight the results, but I think they must not be doing it or why would Ed be complaining about the breakdown of party registration? If the discrepancy between the poll’s breakdown and the national average is a problem, I think that’s what weighting is supposed to correct. You’re right, though, I don’t really know enough about it to say for sure.

(Assuming they don’t weight)…

I agree they should still provide the party splits, even though according to their methodology it shouldn’t really matter that much. The problem is that it opens them up to these insinuations that they’re cooking the results, when really they’re just using ordinary polling methods. If they’re actually running push polls to get Obama elected, that would be one of the biggest journalism scandals of the last 50 years, imo.

RightOFLeft on February 6, 2012 at 3:46 PM

Slimeballs

jake49 on February 6, 2012 at 4:33 PM

I think that you don’t even know what weighting for party ID means, considering your second paragraph.

joana on February 6, 2012 at 11:57 AM

Oh please, Dear, I have taken plenty of university-level statistics courses and use statistics methodology in my business daily.

I’ve also been following these “polls” for well over 25 years. I’ve seen all the “methodology” the pollsters use, and know the difference between weighted and unweighted samples related to Party ID.

Del Dolemonte on February 6, 2012 at 12:20 PM

You don’t.

When you write this:

WaPo has in the past been busted for over-sampling Democrats by 14% or more (I even saw one where they oversampled Dems by 19%) and AP has run a couple of “polls” where they actually sampled twice as many Democrats as Republicans to get the result they desired.

it becomes obvious that you dont’ understand the fact that WaPo doesn’t weight for party ID. How do you know they “over-sampled Democrats by 14%”? Oversampled relatively to what? What’s the standard?

Pollsters don’t adjust for ID. If they get a sample with 60% Dems or 60% Reps, it’s fine.

Back in December of 2011 (December 12-15 to be exact), the WaPo did a “poll” that showed O’bama’s “job approval” to be:

Approve 49%
Disapprove 47%

Their poll sample:

Democrats 32%
Republicans 25%

Yet just a month earlier, the very same WaPo did the exact same “poll”, and got these results:

Approve 44%
Disapprove 53%

Their poll sample:

Democrats 29%
Republicans 26%

See what a difference cooking the numbers can make?

You may toot your own horn as much as you want, but you don’t even get the basics.

Those numbers don’t imply that they’re cooking anything. They just got more democrats in the 2nd poll sample.

And believe me, I see a lot of polls and in the past 2 months it has become much harder to find republicans and easier to find Dems. That’s why you see more and more Dems in the samples – what you ignorantly call “oversampling”.

joana on February 6, 2012 at 4:35 PM

The Washington Polls/AnyoneButConservatives results are not worth the time it takes to read the headline on this article.

chickasaw42 on February 6, 2012 at 4:46 PM

These folks have been caught with their pants around their ankles so many times they have decided to stop bothering to pretend they have pants on. They are full tilt boogey into getting Obama re-elected; ignoring phony polls makes that easier

DaMav on February 6, 2012 at 5:01 PM

RightOFLeft on February 6, 2012 at 11:01 AM

Humm? Don’t know. However 11 months before the 2010 election, Rasmussen Reports was the most accurate poll.

In December 2009, a full 11 months before Election Day, a Democratic strategist concluded that if the Rasmussen Reports Generic Congressional Ballot data was accurate, Republicans would gain 62 seats in the House during the 2010 elections. Other polls at the time suggested the Democrats would retain a comfortable majority. The Republicans gained 63 seats in the 2010 elections.

Other pollsters had the Dems with a + 7 point advantage

DSchoen on February 6, 2012 at 5:11 PM

I have a little “poll” for the folks at the Washington Post to consider.

Over the last few weeks I have talked to some old friends, some of whom I have not talked to for years because of our political differences. Some of them I called and some of them called me out of the blue after many years.

Most of them live in California, some in Washington state. They are of all races, genders and sexual orientation. They are of all income levels and walks of life, too. The thing that all of them have in common is that they are very liberal to ultra liberal and a couple of them are fine examples of the ‘flaming leftard Obamaworshiper’ that we all run into on messageboards and one or two of them have actually worked for the Democratic party. The one common factor with all of them is that they are die hard Democrats and would rather commit seppaku with a rusty butter knife then ever vote for an evil ‘Christiantist’ Republican.

Well, I don’t know exactly what has happened to them over the past couple months but all of them appear to have had a ‘Road to Damascus’ moment. The overall content of these calls can be best summed up in a quote from one of them; “we gotta get that bast**d Obama and the Democrats out of office”. I listened patiently to them as they poured out their thoughts because for many of them this was quite traumatic and frightening because their whole world view was shattering. There was no one else they could talk to about it, either-if they told the people in their social circles they would be ostracized and some might even lose their jobs. I understood this being a recovering liberal who had my ‘Road to Damascus’ moment well over a decade ago.

What these calls indicate to me is that the Democratic party is truly imploding because if they are losing people like these by the time the election rolls around the only ones left in the party will be the truly hard core Marxist/Communists, the ‘race warriors’ and possibly the MSM. The reason why I say possibly about the MSM is from what I have seen over the past week-it indicates to me that some of them are beginning to leave the sinking ship and are trying to save their own necks. It is starting at the bottom and will work its way up.

Nahanni on February 6, 2012 at 6:18 PM

Who still read the Wipe-O?

madmonkphotog on February 6, 2012 at 7:23 PM

And once again, why anyone is polling adults in the middle of an ongoing primary is a complete mystery. That should be likely voters.

Because the poll is meant to shape public opinion rather than measure it?

tom on February 6, 2012 at 9:09 PM

Does anyone really trust WaPo’s poll ? Polls now are meant to do just what tom said; help independents make up their mind – for the next 9 months; discourage Conservatives.

democratsarefools on February 6, 2012 at 9:56 PM

Lanceman on February 6, 2012 at 2:11 PM

Yep. It explains quite a few others as well: Jailbreak and MJBrutus also come to mind.

PatriotGal2257 on February 7, 2012 at 11:39 AM

Is this the information you were looking for?

From http://www.washingtonpost.com/wp-srv/politics/polls/postabcpoll_020412.html

901. Generally speaking, do you usually think of yourself as (a Democrat), (a Republican), an independent or what?

Democrat Republican Independent Other (vol.) No opinion
2/12/12 34 23 37 5 1
1/15/12 32 25 36 5 2

I think the “2/12/12″ notation is a typo. For one thing, there’s no other poll data on the page from that date, and the title of the page has “020412″ which suggests that it was posted before the 12th.

Lou_Shumaker on February 21, 2012 at 11:28 AM

Comment pages: 1 2