Talk Elections

50-42 Obama

http://dailykos.com/weeklypolling/2012/5/31

Last night showed that PPP has a Democratic lean. While some may dismiss bawlexus because they don't like what he's saying, well, he's right - this poll does lean too pro-Democratic.

Yep, PPP results are suspect. That MO O+1 poll in particular was a warning.

Polls this early don't exactly reflect what actual election results will be, some of them don't even reflect the exact results close to the election. National polling as odd swings, the next poll probably will be a lot closer.

There's a simple explanation why this poll is too pro-Obama - the sample. This is with 2012 turnout better for Democrats than 2008, which is highly unlikely.

I'll repeat, national polling has very odd swings (even party ID) and polling hardly ever exactly matches what the electorate will be like, especially not this early. I'm not saying that the poll isn't too high for Obama, but the sample isn't pre-determined, party ID is asked about during the call and after the presidential race is asked about, which is more consistent with an odd swing.

Rasmussen was only two points more accurate than PPP...give me a break.

I made the painstaking journey to the Gubernatorial polls board to have a look for myself at this apparently legendary PPP f-up. They predicted a Walker 3 point victory and he won by 6 and some change on a four point margin of error.

I demand baxlexus and tmth give me my money back after such a lofty promise.

There was no promise - but the results do show that PPP has a Democratic lean, which is what we've been suggesting for a while could be the case.

7, actually, which is what most of the other non trash pollsters said.

A statistically insignificant Democratic lean in one state that could be cancelled out by dozens of polls in other states in 08 and 10 where they landed statistically insignificant to the right.

I'm not saying it's Obama+8 right now, but it's no better than Obama+4.5. There's a MOE for a reason.

Rasmussen polls landed outside of their MOE in 2010, that's why Silver criticized them.  It's an inexcusable result.  That said, I still do not reject Rasmussen polls as, even with their 2010 performance, past results are not indicative of future accuracy.

Well romney cant cure his ills by just picking portman. Romney w that scenario would lose va co and nv. People connect more w obama.

Of course in 08 and 10, PPP didn't repeatedly put out polls to the left of other pollsters. They are now.

PPP was one of the most accurate pollsters in 2010 and 2008 but because of one poll for a special election where they off within the margin of error, they are now a trash poll with a huge Dem bias. Gotcha.

If they reported a number that was off from the actual result by 4 points but there was a margin of error of 4 points, then they did "get it right." That's just how statistics works. 

There's also the fact that all their state polls are far more democratic than other state polls.

Rasmussen/Mason-Dixon are the most accurate in my book. The fact that PPP agrees with most other pollsters means nothing, considering the other major pollsters are Survey USA/CNN-TIME/Quinnipac and other crap.

Indeed. O up by only 8 in Wisconsin? Trash poll.

Thank you for posting this since it shows where Rasmussen is ranked as well. And usually the worst polls for Obama are from Rasmussen. The rest are somewhere in the middle. Including the highly ranked ABC poll which shows Obama up by 3. Do you agree that Obama is probably leading by about 3 points currently, which is also the RCP average (which also absolutely clinched the Wisconsin result)?

adsfasf.

This is not how statistics work!

An absolutely perfect pollster will FREQUENTLY have nights like this, even if they are doing everything perfectly with a perfect sample.

I'm not saying that there isn't some aggregate bias in PPP, but this is an absolute failure of an argument demonstrating any such bias.  Have you even calculated the probability of this size of a miss with a perfect sample?  Have you estimated a house effect using previous polling results?  Anything?

Or are we seriously going, "Idk about statistics, but other pollsters got it right"?  Oy vey.

"Bias" in statistics is not the same as "house effect," which matches the colloquial definition of "bias."  Statistical bias is any deviation from the population parameter.

I read exactly what you were doing.  "But that's pretty poor compared to how many pollsters GOT IT RIGHT" -- Why do you find this meaningful?  You understand that pollsters cannot possibly do better than a perfect sample?  If a pollster averages out to hit within MoE more often than 95% of the time, that does not mean they are better.  That means they are lucky.  Accordingly, observing that other pollsters did better than PPP in one race is a fairly useless analysis.

I replied to your post after reading this comment in another thread: "After a stellar polling job in last night's Wisconsin recall (NOT)."  This comment is misleading.  PPP could have done a perfect job of polling, and a perfect job of predicting turnout, and ~20-25% of the time (just guesstimating) they still would have missed by about 4 percentage points.  You have absolutely no idea from your analysis if they didn't do a "stellar" job of polling.

Repeatedly missing in 1 direction like they did with Amendment 1 is a sign of putting out nonsense.

Poll that shows Romney ahead" Good news! we have a chance of taking america back from the commie!

Poll that shows Obama ahead "Trash poll!"

Trash poll is the automatic response of every dem hack on these boards to a Rasmussen poll.

The poll they do for the daily kos tends to be more Dem leaning than the ones they publish on their website.

Because Rasmussen is objectively a trash polling firm.

The PPP bashing is hilarious. They were off by like 3 or 4 points. Big freakin' whoop. It happens.

You can defend that statement, I suppose, (although it will have a very marginal effect) but how do you defend "After a stellar polling job in last night's Wisconsin recall (NOT)"?  You have rather low confidence (probably less than ~70-75%) that's true.


1. The average systemic bias on gay marriage polls (-7) is greater than the average systemic bias on other polls, indicating it may not just be the pollster's screw-up.

2. Show me something with actual statistical analysis and I will entertain your conclusions.  Otherwise, how do you not know you're accidentally cherry-picking?

I did not say "that doesn't matter."  You are consistently imprecise in both your debates and numerical analysis.

I don't know what that's supposed to mean, but whenever you'd like to respond to points actually included in the words I typed...

So 48-44 without the PPP handicap.

junk poll of course...

Party id sample: D + 9

LOL !

And Romney wins I by 1...

My rule of thumb for PPP polls: add 2 pts to the Republican and subtract 2 from the Democrat, so this would be Obama up 48-44. 
But even that seems a bit optimistic given Ras and Gallup have Romney up 1 today and RealClear has the average of polls Obama up only 1.3%