A Tale Of Two Elections

Jay Cost has recently had two good posts up about the recent polls, here and here.  They’re both well worth the read, but the gist is that the polls are showing variance that can’t be explained just by sampling error.   

Instead, pollsters seem to have two different views of what the electorate will look like.  Indeed, most of the movement that has occurred in the polling average can be explained by different pollsters entering and exiting the average.  Last week the average was at roughly a six-point Obama advantage, but that quickly changed with the addition of the NBC/WSJ poll and the CBS/ poll.  The polls themselves didn’t change much (the seven tracking polls that were in the average at this point have barely moved in their avaerage), but the pollsters in the average have. 

So what we’ve seen is some pollsters, such as IBD/TIPP and Battleground have fairly consistently showed a 3-point race or so.  Other pollsters, such as CBS/NYTimes have consistently been at the high end of the spectrum.  Rasmussen has more consistently been in the middle, with an Obama lead of 6-8 points. 

We see a similar effect in some states. Florida, Minnesota, New Hampshire, and Ohio all have had a number of polls in recent weeks outside of each others’ error margins. Rasmussen and Quinnipiac have consistently been on the opposite ends of the Ohio spectrum.  This is complicated by the fact that individual states tend to be less frequently polled than the nation as a whole, and tend to have less reputable pollsters or less experienced pollsters in them (Big 10 Battleground anyone?), and that their polls tend to have smaller samples, making it more difficult to sniff out outliers. 

The upshot of this is that I’m not sure polling averages will be all that useful this year.  Poll aggregation assumes that the pollsters are working off of basically the same script, and that you can thereby treat them as a single giant sample.  This has the advantage of cancelling (or at least reducing the effect of) the outliers. 

But when the pollsters have fundamentally different views of the electorate for their models, you can’t do this anymore.  If one pollster thinks there will be a massive upsurge in the youth vote, and one pollster doesn’t, and they weight their polls accordingly, then they aren’t working off the same script.  This is always somewhat of the case, but I think it’s more pronounced this time, given substantial uncertainty as to the eventual makeup of the election.  As I said, given the number of apparently outlying polls that Cost identifies, I think that’s the only conclusion we can draw.  Pollsters just aren’t polling the same election.  You may as well try to aggregate the North Carolina and Virginia polls in order to predict Virginia. 

Back in August, I said that the million dollar question this election was the makeup of the electorate  I think that’s still the million dollar question.  If IBD/TIPP or Battleground have the correct model for the electorate, then we can guess that the state polls showing the closer race are the correct ones.  Given that IBD/TIPP and Battleground don’t poll states, we might even see several results to the right of what all the most pro-McCain polls are showing.  And if that’s the case, a comeback and/or a win for McCain is still possible.   

If, on the other hand, Pew has it right, McCain is probably down ten in Ohio, down seven in Florida, down eleven in Virginia, and down five in North Carolina.  In which case, it really is all over but the shouting.  And we can be certain there will be plenty of that. 

But the bottom line is that this isn’t likely to be an election where all the pollsters can write off their error as being the error margin.  Someone is going to be really, really wrong.

Your rating: None Average: 3 (1 vote)


My question is. . .

. . .how do polling companies like Rasmussen establish their weighting numbers?  Is it a matter of self-identification, i.e. asking respondents if they identify more with one party or the other?  Or, do they look at registration numbers - and would the highly inflated numbers that ACORN has been posting have an impact on the weighting?

Uhh...this just seems like

another reason to believe the polling average instead of individual polls.  The turnout/partisan ID assumptions they seem to be making are sort of best-case scenarios in either direction, so it's not unreasonable to assume that the actual result will be somewhere in between... 

Narrow election

FWIW, latest Gallup tracker had it tighten to a 2 point race.

There are so many bogus assumptions in the big Obama lead polls, and no real evidence of GOP defections, PLUS evidence of a bit more Democrat defections, PLUS evidence that 'undecideds' may by McCain-leaning (all whites/latino) that will be the 'bradley effect', plus a McCain trend ... that I would not be shocked if McCain won, and I would be shocked if this was anything but a (0-4pt) narrow race.

As in the last primaries, Obama has had more money and organization, but has not closed the sale but rather been exposed more and more as having socialist tendencies, troubling radical associates, and outside-the-mainstream policies.

Will people take a final second look and decide "Maybe I shouldnt vote for Obama's Socialist-style Change."

Given all that, I wont believe any poll but the one on election day.

there are?

Bogus assumptions, plus evidence of other stuff?  Details, plz.

ask, and ye shall receive...

 Look at:

http://people-press.org/report/465/mccain-support-declines , which are the 'cross-tabs' for the latest pew poll. look at the column marked 'N'. 

Not even bothering to look at all of it, just near the top we can see that the poll was made up of 361 Republicans as opposed to 490 Democrats. We can also see that the poll was made up of 614 college gradutes and a slightly higher (706) number of those who are not. Neither of these are even close to reflecting percentages within the voting population. Compare the income based percentages to those available from irs.gov. All we can really see from this poll is that obama has a big lead among a sample that is better-educated, contains more democrats, and is higher earning than the actual electorate.


Thanks for poll internals

I hadnt even looked at Pew poll. So Obama has a big lead in a sample that is 60/40 skewed to Democrats - who'd a thunk?

Pew = stinker.

I call this garbage POLLAGANDA.

The only polls I've would trust are Ras and Gallup, maybe Battelground. And I am guessing Ras is off a bit (overdoing O numbers) solely because his Dem/GOP weighting is a trailing indicator.



Perhaps there's always hope that Obama's media blitz tonight which will have him everywhere at once will backfire, too.  Over exposure is not necessarily a good thing and perhaps people will just get tired and frustrated at turning on their television and finding him everywhere.  A well-placed and well-crafted McCain spot after each of these Obama-mercials blasting his socialist record -- I'm talking a one minute sound byte including perhaps some of the recent radio feed that surfaced the other day and maybe some of Biden angrily trying to change the subject -- might go a long way towards damaging Obama's credibility.

Who knows.  Maybe there's hope that we won't turn into a US Socialist Republic.

Sean, when will you post your predictions?

You're running out of time, my friend, to post your predictions. In elections past, if I recall correctly, you've posted your prognostications by now. Have you already done so?


No, no my friend.  Not until the Monday before.  In past years I gave more active commentary on the state of the race and where I thought things stood, but this year there's just way too many polls coming out to keep effectively up (note no OxMethod updates recently).  I'll do something on Monday.

Just email me your EC prediction. :-)



If your e-mail on my blog hadn't always been listed as "c@c.com" I might be able to do that.  :-)

It's only a few days to Monday.

Grow up

Yes, it'll be interesting how the final polls match up with the vote count, but in 6 days Obama will most likely be our president. There are a number of reasons for this, one of which is cheap sloganeering.

Stop the 'socialist' crap. Republicans have been using that since . . . ever. It doesn't work anymore. YOU, if you are a republican (I'm a lib.), cannot use that anymore. Republicans (all of them) since and including Reagan have been fiscally irresponsible. All have raised taxes. At some point you have to walk the walk before you talk. And stop blowing people off. Trash the media or 'eletists' and they will trash you.

You cannot damage someone's credibility until you yourself have some. Stop talking about them, and stalk talking about you.

Jeez, I hafta do 2 replies to one post?

 Cr, by saying that you are a 'lib.', I'll assume that you mean 'liberal', and that you might also prefer to be called a 'progressive' or a 'democrat'. I'm a different kind of 'lib', as in 'Libertarian', and all of the words that I just applied to you have been, for well over a century, just nicer ways of saying 'socialist'.

BTW, the only republican in that lot you mention that 'raised taxes' was GHW Bush, and he was a piker compared to Clinton, who in turn would be a piker compared to your messiah. 

In 2006, what you saw was people like me abandoning the republican party and their candidates in droves. What I believe we are seeing in the tightening of the presidential race is the willingness of a lot of us to hold our nose and come back in spite of the country club rats jumping off the ship. We are doing so because we don't like socialism, and given the choice between adding a little more of it or a shit-ton of it, we'll take the canape-sized 'crap sandwich', thank you.

wrong - libertarian

Faced with looming deficits, Reagan raised taxes again in 1983 with a gasoline tax and once more in 1984, this time by $50 billion over three years, mainly through closing tax loopholes for business. Despite the fact that such increases were anathema to conservatives--and probably cost Reagan's successor, George H.W. Bush, reelection--Reagan raised taxes a grand total of four times just between 1982-84.

And ran deficits.

None Dare call Obama the Socialist

YOU, if you are a republican (I'm a lib.), cannot use that anymore


At least until Jan 20,2009 we will still be a in a free country, so I think I will take your advice and roundfile it, along with the previously round-filed demands that every criticism of Barack  Obama be judged racist, or mention of Barack Hussien Obama's middle name considered verboten. Or dragging up cases of Obama actually speaking his mind and exposing his left-liberal elitist biases ...

Obama said this in 2001:

But the Supreme Court never ventured into the issues of redistribution of wealth, and of more basic issues such as political and economic justice in society. To that extent, as radical as I think people try to characterize the Warren Court, it wasn’t that radical. It didn’t break free from the essential constraints that were placed by the founding fathers in the Constitution, at least as its been interpreted and Warren Court interpreted in the same way, that generally the Constitution is a charter of negative liberties. Says what the states can’t do to you. Says what the Federal government can’t do to you, but doesn’t say what the Federal government or State government must do on your behalf, and that hasn’t shifted and one of the, I think, tragedies of the civil rights movement was, um, because the civil rights movement became so court focused I think there was a tendancy to lose track of the political and community organizing and activities on the ground that are able to put together the actual coalition of powers through which you bring about redistributive change. In some ways we still suffer from that.


You can use it . . . freedom of speach and all that

But it just sounds silly. That's why Reps are losing. Instead of actaully talking about real issues, all you hear is cheap sloganeering. Get beyond that . . .  and yes, I consider myself and ELITIST libertarian.

liberal media bias is nothing new

Trash the media or 'eletists' and they will trash you.

BTW, the media has been trashing conservatives since the time of Goldwater... ie before many us were born. NOTHING NEW. They will do it whether we point it out and whine about it or not.

What's new this year is the abject and absoluate amount of total media bias, willingness to be open and blatant about it and the shedding of even a pretense of objectivity. They've gone to be active cheerleaders for the Obama side and active attack dog surrogates in their treatment of McCain/Palin and other Republicans.


Unlike FOX news or Rush

There is a liberal bias in the media, and Reps still manage to win . . . but the the far right goes Rush and FOX which is expressly against Dems. It's not even biased, it's against. I don't see that helping anything: taking a bad situation and being even worse. Good idea.

On any given Sunday

That's why they play the game.

nope - libertarian

Dems don't call themselfs liberals.

My apologies,

 But you did sound like one of 'them'. You'd agree, then, that you and I have to eat a crap sandwich this time, so why opt for the family-size party pack from Subway instead of the finger sandwich? If McCain is president, all of the socialist crap that is likely to be passed can eventually be undone without as much trouble as you might think. Not so if the messiah gets in. How much of the New Deal dreck have we been able to repeal/mitigate in the last 70 years? We'd likely get saddled with just as much of that nonsense now as the country did then. 

no worries

Well, the lasting thing will be judges. But how do conservatives roll back changes? That's a good question, and what and how to roll back? If this is a center right country than Reps by actually being conservative have a natural advantage. Run on your strengths, not against someone's weaknesses. If the rep party continues the normal idealogue propoganda, it undercuts a good message.  People want that. BHO ran on that, and that fact smoothed over his glaring depth of a record. And Reps with keep losing on that strategy. The world is moving on.

That was the gist of my original post. This article is about polling (which will be interesting to see final results), and you have people spouting a litany of  . . . whatever you want to call it . . . and it's not productive. Actually, it's counter productive. Eight years of Bush and negative Rove campaigning just (maybe) likely through out any and all possible gains made from that period . . . for a generation. Barrack didn't win this, Reps utterly and completely lost it.

Are you for change, or against whatever? The republican party needs to step up the game. Whatever you think about Barrack, he's done exactly that. Sitting around crying about the media and mumbling something about socialism is going to help.