Edwards polls best in Iowa when "likely voter" is defined more narrowly

[draft_mario_cuomo]

This helps explain why the polls in Iowa have been jumping back and forth between Edwards and Clinton. The problem with Iowa polling is only a small fraction of people actually vote (5.5% in 2004). The key is defining "likely voters" and how broadly that is defined apparently influences poll results. If it is defined broadly Clinton leads; when it is defined more narrowly Edwards leads.

==So today we have another installment in that pollster's nightmare known as the Iowa caucuses: Two new polls of "likely Democratic caucus goers" conducted over the last ten days that show very different results. The American Research Group (ARG) survey (conducted 8/26-29, n=600) shows Hillary Clinton (with 28%) leading Barack Obama (23%) and John Edwards (20%). And a new survey from Time/SRBI (conducted 8/22-26, n=519, Time story, SRBI results) shows essentially the opposite, Edwards (with 29%) leading Clinton (24%) and Obama (22%).

Is one result more trustworthy than the other? That is always a tough question to answer, but one of these polls is considerably more transparent about its methods. And that should tell us something.

While I have been opining lately about both the difficulty in polling the Iowa Caucuses and the remarkable lack of disclosure of methodology in the early states (especially here and here), the new Time survey stands out as a model of transparency: ==

==I suspect that if we could know all about every pollsters' methods in Iowa, we would see evidence of a disagreement about how tightly to screen and about what percentage of the completed sample should report having participated in a prior caucus.

The resolution of that argument is neither simple nor obvious, but seems to have a profound impact on the results. Surveys that appear to include more past caucus goers (Time, Des Moines Register and One Campaign survey -- see our Iowa compilation) tend to favor John Edwards, while Hillary Clinton does better on surveys that define the likely caucus-goer universe more broadly.==

Read the rest at http://www.pollster.com/blogs/iowa_a_tale_of_two_new_polls.php

[nevergiveup]

1. As an Obama supporter

I look at the ARG survey and think "Yeah!" and then I see the Time survey and think "Damn!". If you try to spin a poll in favor of your candidate you end up re-spinning in a couple of days and you get dizzy and can go nuts. It is best not to get too serious about these surveys unless you see your candidate suddenly getting fewer votes than Mike Gravel.

[jsamuel]

2. absolutely

this has been evident for a while. Clinton polls better when a wider group is selected, same for Obama. Edwards does better when the likely voter model is narrowed down closer. This is why I never lose a wink of sleep over polls going back and forth. Because they aren't. It is all in the methodology.

[draft_mario_cuomo]

3. I agree. If this holds it will help Edwards when the actual votes are counted

Right now the polling suggests a see-saw between Edwards and Clinton, with Obama on par with them in some of the broadly defined Iowa polls. In short, this will make Edwards' victory--if things hold as they are, of course--a bigger deal because it will be larger than expected and hence generate a larger bounce. It would also hurt Clobama because the expectations would be artificially high for them. This is especially the case with Obama. If he averages 4-5 points behind in Iowa polls and is on par with him in the broadly defined ones but winds up finishing 10-11, or even 15, points behind him when voting occurs that will be seen as a very disappointing result for him.

The other thing to keep in mind is in Iowa you need 15% to advance to the final voting stage. Obama, in the narrowly defined polls, is very close to 15%. That means he will not make the cut far more often than Edwards and Clinton which would further damage his Iowa performance, which would be expected to be much better because of the broadly defined polls inflating his numbers.

[robcon]

4. This will only help Edwards if there is a low turnout.

If marginal voters show up at the primary polls, that may mean some trouble for Edwards.

[draft_mario_cuomo]

6. No, it suggests Edwards will do better when the vote occurs

The number of people who vote is always very low in the Iowa caucus. Clinton and Obama's numbers rise when people who are unlikely to actually vote are included in polls. Even then Edwards leads or is on par with them, with the recent ARG being an exception.

[robcon]

8. No , it means 'hard-core' Democratic voters will vote for Edwards...

in higher percents than all Democrats will. If turnout is low, and 'hard-core' voters are in a larger percent of the voters, Edwards has an advantage. If the turnout is high, other candidates (since they get a higher percentage of those marginal voters) have the advantage.

It's just simple math, to me.

[slick8790]

9. But do you really think those who are simply interested in "name brand politics"

would devote all that time on a cold january night to caucusing? I've been reading up on it, and it's much more time intensive than simply voting in a primary.

From wikipedia:

"Participants indicate their support for a particular candidate by standing in a designated area of the caucus site (forming a "preference group"). An area may also be designated for undecided participants. Then, for roughly 30 minutes, participants try to convince their neighbors to support their candidates. Each preference group might informally deputize a few members to recruit supporters from the other groups and, in particular, from among those undecided. Undecided participants might visit each preference group to ask its members about their candidate.

After 30 minutes, the electioneering is temporarily halted and the supporters for each candidate are counted. At this point, the caucus officials determine which candidates are "viable". Depending on the number of county delegates to be elected, the "viability threshold" can be anywhere from 15% to 25% of attendees. For a candidate to receive any delegates from a particular precinct, he or she must have the support of at least that many caucus participants in that precinct. Once viability is determined, participants have roughly another 30 minutes to "realign": the supporters of inviable candidates may find a viable candidate to support, join together with supporters of another inviable candidate to secure a delegate for one of the two, or choose to abstain. This "realignment" is a crucial distinction of caucuses in that (unlike a primary) being a voter's "second candidate of choice" can help you.

When the voting is closed, a final head count is conducted, and each precinct apportions delegates to the county convention. These numbers are reported to the state party, which counts the total number of delegates for each candidate and reports the results to the media. Most of the participants go home, leaving a few to finish the business of the caucus: each preference group elects its delegates, and then the groups reconvene to elect local party officers and discuss the platform."

Hence, the Iowa caucus is more about organization and motivating your base enough to go out and do that, rather than simply making someone like you. And Edwards is excelling at the former, which to me shows he could very well take Iowa.

[Tejanocrat]

10. The Iowa caucus is ALWAYS a low turnout. It is a MUCH BIGGER time commitment than just voting.

[flpoljunkie]

5. Yes, add to that only 5-10% of Iowans actually caucus, and you see how difficult accurate polling is

[draft_mario_cuomo]

7. I agree. In 2004 only 5.5% did

I am inherently biased in favor of Edwards but objectively looking at this as an armchair political analyst, even if the tightly screened polls showed Edwards doing worse, I would put more stock in them. The best way to determine who actually will show up in Jan. is if they have done so in the past.

[Tejanocrat]

11. The Iowa caucus favors candidates with wide support across the state in big cities and small towns

(like Kerry '04), and it disfavors candidates with deep pockets of intense support like young enthusiastic voters in college towns and and highly educated voters in urban centers (like Dean '04).

The format favors Edwards and disfavors Obama, which means that Edwards may likely caucus better than he polls and Obama may not caucus as well as he polls.

The format also favors the "second choice" candidates of those caucus-goers whose first choice cannot gather 15% support at the precinct caucus. I see this favoring Hillary (gaining support as the second choice of disappointed Richardson backers).

I like Obama (he's probably my second choice), but I see Iowa as a race rigged against his style of candidacy. Obama could easily finish third in Iowa, and due to Obama's lack of a bump coming out of Iowa going into New Hampshire combined with Edwards riding a bump out of Iowa, Obama could then finish third in New Hampshire, too. Two third place finishes at the start of the campaign might effectively put an end to Obama's efforts.