I meant to blog this a couple days ago but I’ve been “busy” …
Jim Geraghty at National Review’s Campaign Spot nicely laid out the argument why party ID in matters in polling. This is a hotly contested issue especially since some pollsters weight their polls based on party identification and some do not. Geraghty also does a great job laying out the mischaracterization many in the media make to defend this practice. The don’t have a good answer for our critique so they change the question to answer something they can defend.
First, the basics: Most Democrats are going to vote for the Democratic candidate, most Republicans are going to vote for the Republican candidate, and the independents are usually going to split somewhat evenly. So the proportion of the three groups more or less determines which candidate the polls are going to show ahead. No one claims to be able to predict, with absolute certainty, what the partisan makeup is going to be on Election Day. But we do have a range from recent history — from even in 2004 and a seven percentage point advantage for Democrats in 2008.
Now Geraghty lays out the biggest gap in defenders of current sampling
If a pollster believes that the electorate will be even more heavily Democratic in 2012 than it was in 2008, I’m willing to hear those arguments, but I think it’s a tough case to make.
Now the argument for why turnout will not meet or exceed 2008. Something I have argued many times:
The last presidential cycle was a perfect storm for Democrats — an unpopular GOP incumbent, frustration over wars overseas, a terrifying economic meltdown, a Republican nominee who had spent much of his recent career fighting his own party and who openly admitted he wasn’t focused on economics, the first African-American major party nominee in U.S. history… This year you have Obama running as an incumbent in an extremely tough economy, a more aggressive GOP nominee, the grassroots energy of the Tea Parties, a huge change in each party’s financial resources, the novelty of making history wearing off, and now our embassies under siege in the Middle East… And then there is the shift in the number of voters who are registered voters in each party…
Defenders of the polling mischaracterizing our complaints about sample sizes (I think I got so fired up I commented in Cilizza’s comment section here)
Yet our objection keeps getting misstated and twisted by poll defenders time and again. Here’s Chris Cillizza, claiming the complaints are “a series of false assumptions none bigger than that because the country has been virtually evenly divided on partisan lines for the past decade or so that the party identification question should result in something close to a 50-50 split between Democrats and Republicans.” No. I do not demand an even split, nor do any of the other folks paying attention to this factor. I do think that a split of D+7 or more is excessive, and that a D+3 or D+4 divide — halfway between the GOP peaks of 2004 and 2010, and the Democrat peak of 2008 — is more likely.
The reality
Because for much of this year, in quite a few national polls, we’ve seen Romney winning almost all the Republicans and hold a lead among independents, and still trail Obama, because Obama is winning almost all the Democrats, and Democrats make up such a large share of the sample. Possible? Sure, anything’s possible. But if a pollster is going to offer a hypothetical electorate that looks different from everything we’ve seen before, I’d like to know why they think this is the case…What we see in the most disproportionate poll samples is confirmation bias. To many people covering this race, Romney should be trailing badly, Republicans are flailing desperately, and Obama is running an exponentially better campaign. Thus, it makes perfect sense for the electorate to be even more heavily Democrat than it was in 2008.
28 Comments
Can someone please refer back to the CNN POLL released a few hours before poll closing in WISCONSIN Recall race showing a 50/50 “nail-biter” in their “exit polls” for the Wisconsin recall election. This is the biggest sign of Liberal polling crap-mongering.
NYTimes poll today:
Florida– Obama 48.5 – Romney 48.5
Ohio– Obama 48.5 – Romney 47.5
Pennsylvania– Obama 49.5 – Romney 46.5
Very tight race. The polls will tighten down the line, once Republicans feel like taking polls… I adjusted the +9 D polls to be 0 advantage to either party. Which is what I think will likely happen– a split between ’04 and ’08 turnouts.
Actually, a better thing to do is average the turnout from 2004 and 2008.
So Florida is slightly Republican, which would put Romney ahead (i think that’s fair, Repubs are bullish about FL and Dems a bit worried)
Ohio is slightly Democratic, which would put Obama slightly ahead (where we think it is).
I don’t know Penn but I presume it splits Democrat. So Romney is behind a bit there.
Pay no attention to the Gallup poll behind the curtain. It is just the 47% water buffalo working its way through the boa. By the end of the weekend it will be back to a jump ball.
I don’t think it was the 47%……the weekend saw a massive jump in Obama’s approval overnight. If it was the “47%” it might have affected voting intention and Romney’s ratings, but not Obama’s.
Plus Gallup has NEVER shown such volatility. Even the “Clinton bounce” built up over a week, not a sudden 1 day jump.
I just think it was a strange sample over the weekend which is now flushing through, and/or they have changed their model for some reason.
I agree with John. I believe Romney was gaining the weekend before hence no “effect” was seen in that week of the gaffe in Gallup (because it is 7 day) when it was seen in Rasmussen (3 day that week). Rasmussen evened out by the weekend and we started seeing the effects of the “47%” this past weekend. These numbers will even out as they start to drop off by the weekend (previous 7 day polling)
Keith, your website is fantastic.
What is the Rasmussen party ID breakdown for their national likely voter poll?
Rasmussen changes it every month and I don’t subscribe to his premium service. I believe he did his national polls as D +1 last but but thought I saw somewhere it changed to D +2. This is for his national polling.
his most recent is 37.65% republican and I believe 35 something democrat
Sigh. No, most pollsters don’t adjust by party ID because that’s a very fluid concept that changes both by pollsters and across time. The reason we are seeing higher D samples together with Indeoendents that lean towards the GOP is because a lot of Republicans appear to be identifying themselves as independents. Maybe conservatives who don’t like Rommey too much? They still plan to vote GOP though. If you move those voters from the I column to the R column the D advantage falls, the number of R rises, and the remaining I are more pro dem. but the overall vote doesn’t change.
The “fluidity” concept makes no sense. If you want your poll to be accurate, you weight it by what a reasonable person would expect it to be on election day, which in most people’s minds would be D+2-4. You don’t weight it by some BS “party ID” concept that you pull out of your backside.
And even if the fluidity concept was true, you are still not going to see LESS people identify as Republicans than 2008, the low water mark. And certainly not a drop from 33% to 26-27%, which is where some of these ludicrous polls have it. Most Repubs jumped ship to “Independent” in 2006 and 2008….if they didn’t jump off in 2008 at their lowest ebb they are not going to have jumped off since.
I’m guessing (because I see it repeated over and over whenever the issue comes upZ) that this is the justification used on left-wing sites to make people believe D+infinity polls really are accurate. But deep down, everyone on the Left knows this isn’t so, and that a “normal” turnout will produce a close race or even Romney slightly ahead.
Once again, POLLSTERS DON’T WEIGH BY PARTY ID!!! Except for Rasmussen
Why do so many people keep repeating this nonsense? The reason the polls have the DRI samples they do is because that’s what people responded, not because it’s weighed that way.
Rasmussen hasn’t been around that long (2004), but one can’t argue with the accuracy of their polling (at least their final predictions). Tied with Pew in ’08 as most accurate and also did quite well in ’04. One can go to their website for all their “accolades”.
no but they do weight by demographic. And any of these same polls with as much as 41% dem ID you are also very high African American counts, very high women.and elevated Hispanics and some variation. Demographic weights that match or exceed the counts of 08. Any way you slice it the polls are not really grounded in reality hence the all over the board results.
but if you get 40% Dems and only 20% Repubs responding, does that mean the final turnout will be D+20 on election day? No. it means you just called a bunch more Dems that time.
If you DON’T weight your poll to reflect a likely turnout model, then your poll is rubbish. Simple, ‘d have thought, not sure why so many liberals argue with that.
Yeah sure, every single poll over several months has had more Dems answer than Republicans or Independents.
What is the law of averages???
Ron, Rasmussen has been around since 2000, when they predicted Bush would win the popular vote by +8. Jeez, do you guys make EVERYTHING up?
Guys, guys give it up. I did the same thing in 2004, kept ‘adjusting the polls’ to convince myself Kerry would win. But I learned my lesson.
Obama is ahead, the polls are not perfect but they are clear about this.
Peter go to Huffington or Intrade.we are having adult conversations and you are throwing fits like a four year old.
Harold, I’m trying to educate you. You guys have created an alternate reality and its going to come crashing down in November.
Interesting question I see asked alot but never answered: if Romney is really well behind, why isn’t Obama pulling out of Ohio and Virginia, and pushing into Georgia, Missouri, Montana, and Indiana? Why is he camped out in states he won by double digits last time?
And why has there been such a desperate push to declare the race “over” and dispirit conservatives 6 weeks out? The Dems should just let it play out naturally……..what the conservative base does should not matter if Obama was up by 10 points everywhere.
Petie: Source regarding Rasmussen predicting Bush beating Gore by 8? They only have been around since ’03 http://www.rasmussenreports.com/public_content/about_us
We get it. Rasmussen is way off in your mind. Never mind how they did before. Never mind how the polls looked for Carter or Gore at this time during the race. We get it. Nobody knows how this race wil play out. I have a feeling the events that will determine this race have not yet happened. I sure don’t know if Romney is going to win, but with pollsters that poll year round, he has been under 50% for most of the year. Historically, not a good place for an incumbent.
If Romney wins or gets close with “legitimate” pollsters, I have a feeling we won’t have to have Petie’s keen political ” insight” to enlighten us on everyone’s comments.
And to my friends on this site, feed a troll at your own risk.
Ronnie, Ronnie. I lived the 2000 election and remember how bad Rasmussen was.
http://www.ncpp.org/?q=node/20
Yes Scott Rasmussen got taken to the woodshed after 2000. Like many of the polls that get dumped to the trash heap that are off by high single and even low double digits and the media pretend they never existed and only the couple that were right are spotlighted. After 2000 he determined to never again be that wrong. And in 2004, 2006, 2008, 2010 he was by almost all neutral accounts and some even begrudgenly accounts one of the 2 or 3 most accurate pollsters for elections.
Yes there are some here and out there that are trying to say no Romney is up 25…they are freaks. The point Keith and many of us are making is there is an underlying oddity with the mass of these polls. They don’t seem right to most Americans. I am tryly a dyed in the wool solid middle of the road guy. I am fiscaly conservative, dont care if gays want to marry, abortion i could careless about, religion is pointless to me, the military needs to be cut in size and expense, America needs to get out of the world domination business…that said I surround myself with people on all sides of the spectrum. In 2008, it was a foregone conclusion Obama was a winner it was a matter of how big. No one, not even my hard core right wing few family members thought McCain had an snowballs chance. EVerywhere I looked it was Obamamania. Stickers, signs, people, it was crazy wild.
But this year….there is no thrill. He was the great fixer the guy who was going ot change everything. He said, he promised and we believed he would get it done in 4 years. I don’t know anyone…seriously unscientific….but anyone on any side of the spectrum that didn’t get misty eyed when he took that oath of office as the first black american president. It was cool to be pro-Obama. I just dont see it this year. There is no thrill on eitherside. No one really admits to wanting to vote for Romney, it’s more of a “i’m sick of politics and this BS” mentality. But I also do not hear praise for Obama. I do not hear his name. I don;t see the shirts, the hats, the stickers, the rallies. On the Romney side it seems like people act like its going to work. You don’t want to get up and do it, you are not excited…but you are going to. On the Obama side other than the hardcores…it is a sense of true deflation.
I know this is not scientific but it is palpable that there is no where near, not even in the same city as the ballpark of the thrill of 4 yrs ago. He couldn’t fill the stadium at the convention, he is putting only 5000 in Wisconsin in a state he won huge. And from a pure laymen’s point of view….it is pretty easy to tell a guy on the phone Im going for Obama. It’s another to actually bring your butt out to the polls on a cold November morning and vote for him. In 08 there was the sense among his supporters of they have to have him he is their only chance. This year he let them down.
Poor Peter, trying SO HARD, poor guy….
I try to help those less fortunate than me.
Why do we need “help”? If Romney is really are 10 points behind and you really do believe the turnout will be D+20, then you should be kicking back with a few beers enjoying your inevitable victory. Not spending all day on here desperately trying to convince us your man is ahead.
Unless, of course, deep down you know Obama’s really not ahead by much, if at all.
Actually, although I do want Obama to win, I care less about that than about the nonsense on polls.
Hey Peter is a troll that is going to every conservative website spewing crap…..