Pollster.com

Articles and Analysis

 

Comment of the Day

Topics: 2008 , Likely Voters

Posted by "hobetoo" in response to my post on likely voter models and what effect they may be having this year"

On the possible effect of the enthusiasm gap on the representativeness of polls using registered vs. likely voter screens, I would suggest the following point for consideration.

If candidate A is generating a lot more enthusiasm among his supporters than Candidate B is among his own supporters, then it also seems likely that candidate A's supporters would be more likely to participate in polls. Rather than being underrepresented, then, Candidate A's supporters would perhaps be more likely to be overrepresented than Candidate B's. (I'm thinking of John Brehm's argument that participation in polls is akin to participating in politics, and so the same factors that predispose people to vote are likely to predispose them to consent to an interview.)

 

Comments
brambster:

Enthusiasm is a major factor in Obama winning most of the caucuses. You have to be eager to see your candidate win in order to spend a couple hours or more caucusing for him for her. That enthuisam wasn't absent from the primaries, it was just much less of an effect due to the elimination of the big time barrier.

I'm not sure that you can draw a conclusion between enthusiasm and over-polling however. This didn't seem to be the case with Obama, as he often out-performed the polls in states where the AA population was highest, and one would probably expect the enthusiasm was among the highest there too.

If enthusiastic people are more likely to participate in phone polls, one would also think it would follow that they would be more likely to go out and vote.

Note that these enthusiasm numbers also mirror a trend in how strongly those polled support or oppose a candidate as shown in other polls. This is also reflective of which candidate people think are going to win, and I have seen a 2:1 margin in Obama's favor in at least one recent poll where the race was much tighter between the candidates. So if you don't think your candidate is going to win, would you be that enthusiastic about supporting him or her? Enthusiasm clearly has a strong correlation with which candidate being ahead and/or gaining momentum.

It doesn't seem to make sense to claim that very strong enthusiasm would cause a candidate to underperform their poll numbers, though I could see a reasonable argument in the other direction.

____________________

Uri:

There's also the issue of it being unpopular to be republican at the moment. I can realistically see an older independent who is leaning towards McCain, being called by a young woman from ARG or Rasmussen, and being embarrassed to admit that he's still with McCain. Alternatively, I can see a younger independent who doesn't really care saying that he'll support Obama since it's the hip thing to do.

Also, does anyone know how automated phone polling affects older voters?

____________________

adocarbog:

I agree that Obama voters are more enthused.
I and my wife caucused for him in Iowa. Had to get a sitter for the little kids but we went there just like a bunch of 17 year old kids and 80 year old folks alike.
We are pumped and we talk to our friends to get them to vote. That is why Iowa now (all white conservative state) is almost a lock for Obama in November.

____________________

onelightonvoice:

Well, ask yourself this - if a certain candidate's supporters are not enthused enough to participate in a poll, why would they even show up to the polls?

Enthusiasm was present in the primaries and polls more or less reflected actual elections. And this would change because......

____________________

hobetoo:

Here may be a case in point. Today's Newsweek poll, which shows a far larger support for Obama than shown in other major polls (where are all the independents?), also manifests a much larger proportion of self-identified Democrats than the other polls:

"Obama's current lead also reflects the large party-identification advantage the Democrats now enjoy--55 percent of all voters call themselves Democrats or say they lean toward the party while just 36 percent call themselves Republicans or lean that way. Even as McCain seeks to gain voters by distancing himself from the unpopular Bush and emphasizing his maverick image, he is suffering from the GOP's poor reputation among many voters."

Assuming the sample is not skewed in some way, we can ask: How much of this Democratic party ID advantage in the Newsweek poll is due to a shift in party ID toward the Democrats and how much is perhaps due to a higher level of enthusiasm (and hence higher survey participation rates) among Democrats who are called in the survey?

If it's the latter, then the enthusiasm of Obama supporters may provide an overly optimistic reading of the support for Obama in November. When a pollster calls on the phone, there's no social norm that says you have to participate in polls. However, those who are feeling very positive about their favorite candidate may be more willing to give up a few minutes to answer questions than those who aren't.

But GOTV efforts on election day, commitment to the civic norm of voting ("sense of citizen duty"), and the fact that going to the polls is something of a social (and public) event, may lead even less enthusiastic party supporters to turn out. And so the party ID distribution of actual voters in November, as opposed to respondents to a survey in June, is more likely to be representative of the distribution in the underlying population.

Again this is just my conjecture. And I haven't tried to reconcile the large percentage difference in Democratic party ID or the support for Obama in the Newsweek poll with that in the major polling organizations. There also may well be "house effects" that account for that difference. But I think the question of the representativeness of the party ID figures in surveys, and how they may be affected by enthusiasm in combination with the likely voter screen or other sampling procedures, should be explored.

____________________



Post a comment




Please be patient while your comment posts - sometimes it takes a minute or two. To check your comment, please wait 60 seconds and click your browser's refresh button. Note that comments with three or more hyperlinks will be held for approval.

MAP - US, AL, AK, AZ, AR, CA, CO, CT, DE, FL, GA, HI, ID, IL, IN, IA, KS, KY, LA, ME, MD, MA, MI, MN, MS, MO, MT, NE, NV, NH, NJ, NM, NY, NC, ND, OH, OK, OR, PA, RI, SC, SD, TN, TX, UT, VT, VA, WA, WV, WI, WY, PR