Don't trust the unweighted exit polls! trust-the.html

Following up on a point I made yesterday -- in a post that just got Instalanched -- as we political junkies giddily await the first hints of what's happening in Pennsylvania today (finally, another primary!! election results tonight!! exit polls!!! colorful maps!!! whee!!!!), it's very important for us, and even moreso the media, to remember that Obama almost always does well in the leaked, unweighted exit polls, and almost always does less well in the final results. For instance:

In New Hampshire, the "first wave" showed Obama leading by 4; he lost by 3.

On Super Tuesday, the "first wave" had Obama winning New Mexico by 6 (he lost by 1) and losing California by just 3 (actual margin: 8). The "second wave" wasn't any more accurate: it had Obama winning Georgia by 50 (actual margin: 35), Illinois by 40 (actual margin: 32), Alabama by 22 (actual margin: 14), Delaware by 14 (actual margin: 9), Connecticut by 7 (actual margin: 4), Arizona by 6 (lost by 8), New Jersey by 5 (lost by 10), Missouri by 4 (actual margin: 1), Massachusetts by 2 (lost by 15), and losing Tennessee by 10 (actual margin: 13), New York by 14 (actual margin: 17), Oklahoma by 30 (actual margin: 23) and Arkansas by 46 (actual margin: 44). So Oklahoma and Arkansas were the only states on Super Tuesday where Obama did better than the leaked, unweighted exit polls suggested.

On March 4, the "second wave" showed Obama winning Vermont by 34 (actual margin: 21), Texas by 2 (lost by 4), Ohio by 2 (lost by 10), and tied in Rhode Island (lost by 18).
Averaging all those numbers together -- and I recognize that this is very unscientific -- you get an average discrepancy of 7 to 8 points. That is to say, Obama generally does 7-8 points worse in the actual results than he did in the leaked, unweighted exit polls.

This is crucially important, because it has the potential to significantly affect the post-primary "spin." That's exactly what happened on Super Tuesday, when Clinton was able to initially spin a "victory" out of her lukewarm performance, largely because the media was expecting Obama to win some "big states" based on those early, favorable numbers. Likewise on March 4, Hillary was able to claim "success" for her Texas and Ohio "firewall," even though she really needed much larger margins to make meaningful delegate progress, in part because the leaked exit polls again conned the punditry into expecting better showings by Obama, possibly including a win in one or both states.

It'll be a travesty and a farce if that happens again. Hillary Clinton needs to win big -- like, double digits big -- and make significant delegate gains in order to claim any kind of a meaningful victory in Pennsylvania tonight. That basic fact will not change one iota if Drudge and The Corner and Talking Points Memo and the Huffington Post (and, er, the Irish Trojan) publish initial, meaningless numbers this afternoon that show a "OMG A DEAD HEAT IN PENNSYLVANIA!!1!" and then Hillary "pulls away" and wins by 6 or 8 points or whatever.

It's important to remember that these leaked exit polls do not actually represent any version of reality; they are not something that a candidate can "come back" from. In those instances where they differ from the actual numbers, they are, and always were, simply wrong. The exit-poll-fueled "seven-hour presidency of John Kerry," for instance, was always an illusion; Kerry was never "ahead," and Bush never mounted a "comeback." That's all pure perception, and has nothing whatsoever to do with reality. Same thing here. If Hillary, yet again, does substantially better than the exit polls suggest, nobody should be surprised, and still less should she get favorable, "expectations"-based spin as a result. Obama's early "lead," in that event, will have been (again) a complete chimera. So please, for heaven's sake, let's not get all excited if history repeats itself again.

As I said yesterday: Fool me once, shame on you. Fool me 21 times, shame on me.

P.S. Politico adds an additional cautionary note, referring to actual returns rather than exit polls:

Don't be fooled by early results. The cities and suburbs usually report their returns first, which gives the candidate favored in those areas a quick - and sometimes fleeting - lead. The conservative-leaning small towns through the center of the state usually filter in much later in the evening.

This tendency has wreaked havoc in past elections: A Democrat goes to bed thinking he or she is the winner, but wakes up the loser. The last time it happened was 2004, when the Associated Press called the state attorney general race for Democrat James Eisenhower and retracted it later in the night as the numbers closed. Some newspapers went to print with the wrong results.

So Obama could show a lead in the early results, but it might be short-lived. If Clinton is ahead at the start, she may never lose it.

There's more...

The American Prospect: Obama will win Pennsylvania

That creaking noise you hear is the sound of me going way out on limb to predict that Barack Obama will win the Pennsylvania primary on Tuesday, finally ending Hillary Clinton's presidential ambitions.

After all sound and fury, the race in Pennsylvania will come down to the strength of get- out-the-vote (GOTV) operations, and I think Obama's campaign's organizational advantages will be enough to push him past Clinton by almost two percentage points. He's got money, he's got energy and enthusiasm (despite his debate performance on Tuesday), and he's got Philadelphia and its suburbs

Broadly speaking, presidential elections are almost always decided by what and who Americans think best suits the moment. After all the wins and losses, after all the gaffes, the deceptions, and the rare moments of inspiration, Obama, is simply closer to the mood of the country than either Clinton or McCain.

Obama is selling change. Both of his opponents are selling the virtues of experience, but voters, fed up with the way things have been going, view experience as more of a problem than a solution.

Still, it's an election and Obama can blow it (he erred in, among other things, not anticipating the controversy over Rev. Wright ), but he has shown himself capable under attack and in Pennsylvania he has some underreported advantages.

At first glance, Pennsylvania, one of the whitest, oldest, and most working class states in the country, should be Clinton's to lose. The demographic numbers are indisputable, but the beating heart of Democratic politics in the Keystone state is Philadelphia -- and now, its suburbs -- and the whole region is indisputably in the Obama column.

Since Election Day 2007, 306,686 people have registered as Democrats in Pennsylvania -- more than 45 percent of them (139,000) in Philadelphia and the Philly 'burbs. And two college counties, Centre, 19.6 percent (Penn State), and Union, 17.3 percent (Bucknell University) are in the top three counties in terms of the percentage increase of new Democratic voters. Again, it's fair to most new registrants are Obama voters. He will not win Northeast Philadelphia or some precincts in South and Southwest Philly, but he will still win by a large margin in the Philadelphia region.

The path to an Obama win is relatively straight forward: run up the numbers in and around Philadelphia, fight for and maybe even win the Lehigh Valley cities Bethlehem and Allentown, and minimize his losses in the west. This is a strategy that tracks with Democratic victories in Pennsylvania in recent years.

Here, finally, is why I think he wins:

Clinton hasn't succeeded in making any of her criticisms of Obama stick. He has managed to weather scandals that would sink politician of lesser skill.

Clinton has been most effective when she is seen as the victim and underdog, but, given her aggressive response to Obama's "bitter" comments and her established strength in Pennsylvania neither of these circumstances apply. If can resist the urge to complain about his treatment in the debate he may be the one seen as a victim.

Bob Casey, Jr.
The importance of the Casey's endorsement of Obama is hard to overstate. In part that's because Pennsylvania's junior senator is as daring as a piece of Lackawanna anthracite coal and is seen as unwilling or unable to play cynical political games. What's more, he is an able counterbalance to Clinton's two biggest supporters -- the affably pugnacious Gov. Ed. Rendell, and Philadelphia's African American Mayor Michael Nutter.

Casey is also exactly kind of conservative, Catholic, blue-collar Democrat that Obama is supposed to have the most trouble attracting. He needs Casey's help all the more now that some of these voters think that he sees them as clinging to guns and religion out of a sense of economic frustration. In a new ad for Obama, Casey makes the election clearly about the economy, declaring on camera that "in towns like yours and mine, families are struggling with bills they can't afford and jobs moving away. It has to change -- but it won't until we change Washington."

But Casey's endorsement does something less obvious for Obama -- it rescues him from being the 'Philadelphia candidate' and all the taint of racialized politics, corruption, and urban decay that such a label would put on him. This is especially true when Casey's support is contrasted with Rendell's and Nutter's, since both are current or former mayors of Philadelphia.

So my call is Obama by a point and a half. Creak ... why_obama_will_win_pennsylvania

There's more...

14 New SurveyUSA statewide GE polls out

From the diaries. Obama could run for Governor of Iowa as an Illinois resident and win, but can he break out of the 20's in Kentucky against Clinton or, if he gets the nod, against McCain? More seriously, Virginia seems in the pocket of McCain again, jerome

These come with the usual caveats about April polling for a November contest. But, someone will eventually post them, so why not me? Nothing too different from their last report (summary in links at bottom).  


Clinton 56
McCain 41

Obama 48
McCain 46

New Mexico:

Clinton 46
McCain 49

Obama 44
McCain 50


Clinton 47
McCain 46

Obama 42
McCain 50

New York:

Clinton 55
McCain 39

Obama 52
McCain 43


Clinton 53
McCain 42

Obama 45
McCain 47


Clinton 47
McCain 46

Obama 51
McCain 42


Clinton 39
McCain 55

Obama 44
McCain 52


Clinton 47
McCain 46

Obama 49
McCain 43


Clinton 46
McCain 46

Obama 49
McCain 44


Clinton 36
McCain 57

Obama 37
McCain 54


Clinton 34
McCain 60

Obama 32
McCain 64


Clinton 53
McCain 40

Obama 50
McCain 43


Clinton 42
McCain 48

Obama 49
McCain 42


Clinton 46
McCain 48

Obama 29
McCain 63 spx 04/17/april-head-to-head-contests-six-st ates-flip/

There's more...

Reporting poll results: a double standard?

Jonathan wrote in SUSA Clinton Holds 16-Point Lead in Indiana /17200

"The SUSA poll was in the field Friday through Sunday and had a margin of error of plus or minus 4.2 percentage points. As a result, the movement in the poll was not statistically significant."

While this is technically true, I will ask several questions and make several comments.

1.  The previous poll from IN (SUSA) was Clinton +9.  What would you be writing (and what would the Obamacrats be saying) if it went 7 points the other way to Clinton +2?

2.  I submit that all the Obamacrats here would be all over the "movement" in the polls.  Just recently, Liberal Avenger was talking* about "movement" within the Quinnipiac poll from PA which went from Clinton +9 to Clinton +6  * 5/4902 Even though there was no movement in the poll, everyone was writing Clinton's obituary because the polls were "tightening" based off Quinnipiac, according to Liberal Avenger anyway.

3.  Since the movement is not "statistically significant," what does it matter if Clinton is now up 16 or 2 in Indiana?  It's all the same, right?  In your words Jonathan and those of statistical significance, they are both the same.  Yet, experience in the real world tells us they are not the same.  If you think they are, would you rather be up +16 from +9 or up +2 from +9?

In the future, I urge everyone to post with the same skepticism of the MOE as Jonathan did in his piece about Indiana.  Moreover, Clinton and Obama supporters should stop talking about "movement" unless the movement is 2x MOE, since that is what constitutes statistical significance.  

Accordingly, if in SUSA's newest weekly release on PA, Clinton is "down" to a 13 point lead from an 18 point lead a week ago, it should be reported that there was no movement, ditto if she is up 23 in their latest poll; the movement in either scenario would be within the MOE.

The reporting of polls is an important part of spin, so I doubt any of this will be absorbed in the collective conscience.  But, it's worth noting nevertheless.

Just think of how many times you've seen someone on either side here talk about "movement" when a poll changed from 45-44 to 47-44.  As educated people, you should know better than to spread such falsehoods.

There's more...


Advertise Blogads