Is PPP cooking its numbers to fatten Akin up for a McCaskill kill?

[Torie]

Why has the PPP sample suddenly got so Pub with its poll, that is the question.  What do you polling junkies think?  Is PPP just a hack firm that is in the tank for the Dems, but clever enough to make it hard to find the smoking gun to out them on it?  Will their numbers suddenly get more Dem once the "real" deadline for Akin to get out on Sept 21 or whatever passes?

Explain to me why this is just more Pub paranoia, and that we just need to up our meds. Thanks.

[RogueBeaver]

Jensen has been caught putting his pinky on the scale but surely wouldn't be so silly as to slam his fist on it. I'd like to think that's what happens when you do a 1-day rush poll.

[Linus Van Pelt]

This is from PPP's own description of their methodology (except the bold, my emphasis):

You must be logged in to read this quote.

So one should expect their partisan samples to vary somewhat randomly from poll to poll, with occasional extremes to either side.

[Torie]

This is from PPP's own description of their methodology (except the bold, my emphasis):

You must be logged in to read this quote.

So one should expect their partisan samples to vary somewhat randomly from poll to poll, with occasional extremes to either side.

That sounds like a flawed methodology. In the end, partisan affiliation trumps all the rest when it comes to polls. Pollsters say folks change their minds about their partisan affiliation on the edges, all the time, on a day to day basis, or week to week or whatever, so no worries. The sample is pure, but the minds of this vacillating cohort of voters are mush, that's the rap. But a change of this magnitude?  Really?

Anyway, here is a link to a bonus video, starring Piers Morgan.

[Brittain33]

Dunno, but their polls today show Scott Brown up 5 and Romney up 1 in Wisconsin, so it's not just Missouri. I blame the overnight sample myself.

[Talleyrand]

Probably the issue with doing a snap one-day poll as RogueBeaver pointed out. I think they should do another one soon to see if this was an outlier. And I genuinely believe Akin is still slightly favored to win this election, so I wouldn't discount this poll completely, though I do think he's down a couple of points ATM.

[Linus Van Pelt]

This is from PPP's own description of their methodology (except the bold, my emphasis):

You must be logged in to read this quote.

So one should expect their partisan samples to vary somewhat randomly from poll to poll, with occasional extremes to either side.

That sounds like a flawed methodology. In the end, partisan affiliation trumps all the rest when it comes to polls. Pollsters say folks change their minds about their partisan affiliation on the edges, all the time, on a day to day basis, or week to week or whatever, so no worries. The sample is pure, but the minds of this vacillating cohort of voters are mush, that's the rap. But a change of this magnitude?  Really?

This is a controversial topic in the polling industry. Traditionally the orthodox view in statistical theory is that one should only reweight for demographics where the distribution among the population is independently known from a non-polling source. By this standard party ID should not be used, since it is only known from other polls which may be just as biased demographically. (Party registration is known in a little over half the states, but generally pollsters are asking a standard question about party ID in all states that isn't applicable across different partisan registration regimes).

For this reason the traditional large polls generally do not re-weight by partisanship. In addition to PPP, none of Gallup, Pew, Quinnipiac, or the national network polls do this. Rasmussen by contrast does so, as do many smaller outfits.

[TJ in Oregon]

Reweighting can be just as bad because the electorate you're weighting to could be as flawed as the poll's sample. A prime example of this would be Rassmussen in the 2010 cycle. It's a pick your poison situation.

[DrScholl]

First PPP is supposed to have sampled too many Democrats in polling, now it is sampling too many Republicans? This race is heavily partisan, it's not surprising that Akin was still managing a tie.

If you think they sampled too many Republicans in Missouri, perhaps they did the same in Wisconsin, where Romney posted a 1% lead in their poll there.

[Nichlemn]

I don't think it's implausible that this controversy might not make much of a difference. He was making a claim with a grain of truth without a great deal of confidence, and then quickly retracted it. If he'd explicitly said what some people have inferred (if you get pregnant, then you weren't really raped) and/or dug done and refused to retract his comments, he'd be in a lot more trouble.

[Torie]

Gang, we are dealing with something potentially more serious here. It is about motive and mens rea. Is this poll just a function of incompetence, or at the margin of error to the Pubs, meaning either just negligence, or statistical noise, or are we dealing with a deliberate cooking of the books, meaning that PPP is engaging really in deliberate fraud. Presumably if so, the motive is to save McCaskill, but anyone that is what motivated me to put up this rather vanity oriented thread. There are potentially some noisome zephyrs emanating from a certain castle is Denmark suggesting that something is very rotten inside. The timing is the thing to boot. This poll is generated at warp speed, just in time to give a temporary life raft talking point for McCaskill's life raft, just 24 hours of what was perceived as the deadline for Akin to get out. So dot 1 is connected to dot 2 which is connected to ... ?

We probably will never know. The is no reason to be optimistic that we will get any glimpse of just how tangled the web to deceive really was, if at all. Just like the Unfinished Symphony, some operas never get to the point where the fat lady sings. The cast gets drunk during intermission, and thus no second act.

[Meeker]

Truthers... birthers... "pollthers"?

[Likely Voter]

http://hotlineoncall.nationaljournal.com/archives/2012/08/robopoll-convin.php

You must be logged in to read this quote.

[muon2]

http://hotlineoncall.nationaljournal.com/archives/2012/08/robopoll-convin.php

You must be logged in to read this quote.

The problem for the candidate is that stories like Akin's statement take time to root in people's minds. A snap poll isn't at all helpful and the views of other seasoned politicos are probably more accurate in gauging where a gaffe like that is headed. A poll taken a few days later has far more meaning since then the long-term impact on voters can be judged.

[Eraserhead]

A tremendous victory for the sanctity of RAPE!

Seriously though, I'm wondering if PPP is trolling a bit here and massaged their head-to-head numbers in order to help Akin look stronger than he is. Given the fact that they're Ds at the end of the day, it's not surprising that they'd want him to stick around. You're not going to win anything with favorables like that and the money will be cut off. And there's that sample that Tender posted for the poll. Umm, yeah. So I still think he's toast, one way or the other. This will give him a talking point to help get through the next few days though. "See, the latest poll shows that I can still win!" Very sneaky, PPP!

Now, let's see if Rasmussen comes out with a poll that has him trailing by 10 to counter this.

Just call me Nostradamus, because that Rasmussen poll has now arrived.

http://www.rasmussenreports.com/public_content/politics/elections/election_2012/election_2012_senate_elections/missouri/election_2012_missouri_senate

[bgwah]

^haha, wow. I mentioned PPP may be boosting Akin... but I didn't mention Ras, much less predict his margin. Good job!

[Eraserhead]

^haha, wow. I mentioned PPP may be boosting Akin... but I didn't mention Ras, much less predict his margin. Good job!

Thank you, thank you.

[Likely Voter]

http://hotlineoncall.nationaljournal.com/archives/2012/08/robopoll-convin.php

You must be logged in to read this quote.

The problem for the candidate is that stories like Akin's statement take time to root in people's minds. A snap poll isn't at all helpful and the views of other seasoned politicos are probably more accurate in gauging where a gaffe like that is headed. A poll taken a few days later has far more meaning since then the long-term impact on voters can be judged.

I agree. My point in posting that is that PPP poll agreed with Akin's internal poll. But I noted in another thread that a single night of polling on the day this thing blew up was pretty meaningless. It has nothing to do with PPP cooking books, except that doing such a snap poll was dubious to begin with.

Of course now there will be conspiracy theories that Rasmussen is cooking the books to force Akin out. Which are just as dubious.

[Eraserhead]

http://hotlineoncall.nationaljournal.com/archives/2012/08/robopoll-convin.php

You must be logged in to read this quote.

The problem for the candidate is that stories like Akin's statement take time to root in people's minds. A snap poll isn't at all helpful and the views of other seasoned politicos are probably more accurate in gauging where a gaffe like that is headed. A poll taken a few days later has far more meaning since then the long-term impact on voters can be judged.

I agree. My point in posting that is that PPP poll agreed with Akin's internal poll. But I noted in another thread that a single night of polling on the day this thing blew up was pretty meaningless. It has nothing to do with PPP cooking books, except that doing such a snap poll was dubious to begin with.

Of course now there will be conspiracy theories that Rasmussen is cooking the books to force Akin out. Which are just as dubious.

And you don't think the professionals at PPP realized that?

[Likely Voter]

Apparently McCaskill is joining the conspiracy theory that Ras is trying to force him out. She tweeted: “Rasmussen poll made me laugh out loud. If anyone believes that, I just turned 29. Sneaky stuff.”

And the Akin campaign are using Ras as proof that McCaskill should drop out (you read that right)
http://2012.talkingpointsmemo.com/2012/08/todd-akin-claire-mccaskill-drop-out.php

[Torie]

A tremendous victory for the sanctity of RAPE!

Seriously though, I'm wondering if PPP is trolling a bit here and massaged their head-to-head numbers in order to help Akin look stronger than he is. Given the fact that they're Ds at the end of the day, it's not surprising that they'd want him to stick around. You're not going to win anything with favorables like that and the money will be cut off. And there's that sample that Tender posted for the poll. Umm, yeah. So I still think he's toast, one way or the other. This will give him a talking point to help get through the next few days though. "See, the latest poll shows that I can still win!" Very sneaky, PPP!

Now, let's see if Rasmussen comes out with a poll that has him trailing by 10 to counter this.

Just call me Nostradamus, because that Rasmussen poll has now arrived.

http://www.rasmussenreports.com/public_content/politics/elections/election_2012/election_2012_senate_elections/missouri/election_2012_missouri_senate

Yes, indeed. I still think the odds are high that Akin will be out.

[Beet]

A tremendous victory for the sanctity of RAPE!

Seriously though, I'm wondering if PPP is trolling a bit here and massaged their head-to-head numbers in order to help Akin look stronger than he is. Given the fact that they're Ds at the end of the day, it's not surprising that they'd want him to stick around. You're not going to win anything with favorables like that and the money will be cut off. And there's that sample that Tender posted for the poll. Umm, yeah. So I still think he's toast, one way or the other. This will give him a talking point to help get through the next few days though. "See, the latest poll shows that I can still win!" Very sneaky, PPP!

Now, let's see if Rasmussen comes out with a poll that has him trailing by 10 to counter this.

Just call me Nostradamus, because that Rasmussen poll has now arrived.

http://www.rasmussenreports.com/public_content/politics/elections/election_2012/election_2012_senate_elections/missouri/election_2012_missouri_senate

The problem with the Rassy poll is that it's 48-38. The number of undecideds is too high. Basically, there are a significant percentage of people who probably want to vote Aiken, but can't bring themselves to push the button right now. What I'm getting from that Rassy poll is a 4 or 5 point race.

Also, Crossroads GPS hasn't pulled their October buy.

[Likely Voter]

Those outside groups are hoping that by the end of September Akin will be out and they can back the new candidate.

The question is: what do they do if Akin doesnt pull out and the race is close. My bet is they will run ads attacking Obama that also mention McCaskill so they can pretend they are just backing Romney (even if Romney is already well ahead)

[riceowl]

Apparently Scotty has Obama +1 in the state today.  And they say PPP is cooking the books...