The Marist poll out of Ohio that showed President Obama with a 7% lead among likely voters over Governor Romney used a sample that had 10% more Democrats than Republicans –a 2% greater advantage than occurred in 2008 at the height of Obamamania! I’ll ask the poll’s director, Professor Lee Miringoff, for an explanation of the sample on the first segment of today’s program and will post the transcript here later today.
Whatever sample is being used and by whatever poll, it is simply journalistic malpractice not to tell the reader what the sample make-up is. Perhaps it is defensible; perhaps it isn’t. But it is information impacting the reliability of the “result,” and the subscribing public has a right to know. RealClearPolitics.com also needs to start tossing outliers like marist in Ohio out of its “RCP average.”
HH: I want to begin with the presidential race today. It’s my opportunity to talk with Lee Miringoff. He is the director of the Maris Institute for Public Opinion. And Dr. Miringoff, welcome, it’s great to have you here.
LM: Hey, it’s my pleasure. How are you today?
HH: Great. I was up in your neck of the woods. I was at Hyde Park last Saturday, drove past the beautiful Marist campus there.
LM: You should have stopped in. We could have given you a guided tour. You probably were just in time for the 12:07 tour of the campus.
HH: Well, I had to get to, I’d never been to the FDR Library before, so…
HH: Priorities, priorities…Next time.
LM: Next time, we’re, just as you say, it’s a beautiful campus right on the Hudson, and we are about four miles south of where you were.
HH: Yeah, it’s gorgeous. Now I want to talk about polling with you. This is not hostile. I’m just genuinely curious. The Marist polls that the Journal, Wall Street Journal ran with show Barack Obama ahead of Mitt Romney in Ohio by seven points.
HH: And the screen, the sample size, was 38% Democrat, 28% Republican.
HH: Ten point spread. How does that yield a good result?
LM: Well, in the exit polls last time, if I’m not mistaken, it was an eight point spread. So it’s within the error margin of what it was last time. And you know, party ID is not fixed in stone, either. It does vary somewhat. So yes, you know, the numbers are showing, we think, a pretty accurate and important indication of where things are, stand. In Florida, I think it was a one point difference, and in Virginia, it was a two point difference going the other way. So I mean, that, both polls, all three states are within two points, I believe, of what they were in the party ID last time. Of course, the last time is based on the exit polls, which are also polls. So it’s nice to have a barometer. You want to be in the ballpark. But it doesn’t mean that last time was exactly going to replicate itself this time. That’s why we interview so many people in our surveys, and why we filter down to likely voters, which you correctly identified.
HH: But now for the benefit of the audience, the actual result in 2004, George W. Bush won by 2%. In 2008, President Obama won by 5%. You are right. The exit polls showed Ohio at an 8% greater turnout of Democrats four years ago.
HH: But as HotAir’s critic wrote of the poll, “The Democratic turnout advantage in this Marist model would only be a point less in Virginia and Florida than it was at the apex of Hope and Change in 2008. And in Ohio, it would actually be two points greater.” Is there some level at which, I mean, how did you arrive at 38-28, Dr. Miringoff?
LM: Well, what you do, you don’t pick the number. It’s based on the interviews with the people you do. So it’s not like you’re punching in a 10 point party spread. It’s based on the interviews and who remains in the pool. You don’t want a three credit lesson right now in survey research, I’m sure.
HH: Oh, but I do, actually, because everyone right now believes that the polls are biased to President Obama because of this kind of a sample. So I really am genuinely interested.
LM: Well, let me correct you right off the bat. A sample that has two percentage points more in one survey, Democrat, and another state has a Republican a point more, this is all very much within what’s called the error margin. There’s nothing that in any way resembles any bias in the sample. And in fact, the truth of the matter is the internal of the polls, the campaigns were totally comfortable with…if they didn’t like the results, you would have heard from both campaigns by now.
HH: But I mean, again, for the record, for the audience, ARG today says Obama’s up 1 in Ohio. Rasmussen says Obama’s up 1 in Ohio.
LM: Well, you have to understand also that there’s a difference between using live interviewers who call cell phones, and polls which use robocalls in terms of their scientific basis and their dependability.
HH: I understand that, and we…
LM: Let me finish the point, please. If you do not use cell phones in your surveys, as a lot of the surveys don’t, you’re missing what is most of the Obama margin, because right now, about 30% of the households, and the likely voters in each of these states, are cell phone only. And in fact, I could give you the numbers, but you don’t want to get bored by the statistics. The truth is that most of the Obama margin is based on the cell phone, which are obviously younger people and people who are minorities. If you don’t have cell phones in the sample, you’re going to find a one or two point difference in the race. We do also among our land line only respondents.
HH: So what I go back to, though…
LM: So inconsistency, there is an issue of how scientifically based, and how the polls are conducted.
HH: That’s what I’m trying to get at, the scientific basis for a 10 point Democratic advantage. And this is where I’d like you to unpack it for…
LM: Well, you say a 10 point Democratic advantage…
HH: Dr., let me…
LM: When the exit poll was eight last time. So it’s not like it’s…
HH: Well, let me, I’ll set it up for you. I’ll tell you what’s on people’s minds. I’d really love to hear you answer it, which is that was the height of the President Obama Hope and Change movement. He was extraordinarily strong in November of 2008. Right now, 60% of the country think we’re on the wrong track. The national polling, Rasmussen says Obama’s behind by three. CBS/NYT says he’s up by three. His favorability ratings are significantly down over what they were in 2008. Against that backdrop, what level would you become concerned as a professional pollster that you had oversampled Democrats? I know you just said two percent is within the margin of error, but to many people looking at this, it’s not credible to say that the Republicans will be outpolled in Ohio by ten points in November by Democrats. It just doesn’t make any sense to us.
LM: Well, you know, let’s put it this way, and I’ll go back to what I just said. Let’s take Ohio, which is the one you seemed to be identifying the most.
HH: I’m from Ohio. That’s why I’m asking.
LM: Among land line respondents, our numbers were 49-45 favoring Obama over Romney, a four point difference, which is within a point or two away, I think you were saying, the Rasmussen and ARG polls were doing, both of whom, I should point out, are generally seen as not using thorough methods, but that’s a different question entirely for a different time. Obama’s head by 14 points among cell phone only. If they aren’t doing cell phones, then they’re missing that group. Our number is four points difference between the two candidates. And I think also, you know, let’s look at, these are not done in isolation from each other and from the times in which they’re done. This poll is clearly done coming off of the Democratic convention. All the polls, I think, with few exception, all the reliable polls are showing that there’s been a significant bounce as a result of the Democratic convention. Some are showing two points, some are showing five points. The Gallup poll has been showing Obama now with a six or seven point lead nationally. No reason to think that the battleground states would be less than what the national numbers are. Does the bounce last? We’ll find out in a couple weeks. Is the bounce real right now? Almost all the polls are showing it. To look at four years ago and say that was Hope and Change, and that was the peak, well, he’s getting less right now, Obama is, than he got four years ago. It’s that Romney is getting a lot less than McCain got. So you’re talking about a point spread. If you were in my class, I’d tell you don’t just look at the margin. Look at what the incumbent is getting, getting 50%.
HH: Dr. Miringoff, I’d be in the front row, I really would, and I’d ask you again, because I teach Con Law, and I understand slow students, so maybe I’m just slow. But my question hasn’t been answered, which is a ten percentage point Democrat sample advantage over Republicans undermines, in my view, the credibility, when at the height of President Obama’s popularity, the exit polls show 8%. So at what point, I’ll make it a very simple one. At what point would you be alarmed? Is it 15% gap, or 17%? What point would you say…
LM: Well, I’ve answered the question three different ways. I’ve said that the polls you’re using to compare us to are not the accurate ones.
HH: No, I’m not comparing you. I’m asking…
LM: Well, you did. You cited Rasmussen and ARG…
HH: No, but right now…
LM: …as indicators that the race was closer, and I obviously don’t agree with that.
HH: No, but that’s a source of confusion. What I’m asking you now is specifically only about your sample size. Not their sample size, not their methodology. At what point would you be worried about your sample size?
LM: It depends on the race, because as I said, the exit polls that you’re building this whole structure around, and there’s so much more to talk about than this, but I’m happy. It’s your program. We can do that. The exit polls that you’re talking about are polls in and of themselves. Things change over four years. It’s not just the seven point spread that you’re pointing out. And obviously, Obama, you know, did fine last time. But he had more than 50% in Ohio. He’s only getting 50% now. So you could also say, equally, that only 50% are pointing out that they’re going to vote for him. 50% are going for Romney or are on the fence. Now if those other people who are on the fence move to Obama, then the race gets very close in Ohio. So don’t just look at the seven point spread and say well, that’s night and day, and that’s the whole can. It doesn’t have to be…
HH: It’s not. I just, honestly, I’m not trying to undermine your credibility. I just don’t get at what point you would be alarmed by the sample size. And so I guess I’ll finish up by…
LM: I haven’t had a poll like that in 30 years of polling, so I’ve got a long…
HH: But that’s not the question.
LM: So I’m not going to get alarmed at this.
HH: Dr., that’s not…
LM: It won’t happen. It doesn’t happen.
HH: But the question is, you’re an academic. As a professional, at what point would you say that sample size, given what we know, is not legitimate? Is it 15%?
LM: Well, here’s what you could do. You could go back and look at a 2004 exit poll, and look at 2008, and you could say oh, wow, look at 2004. That wasn’t at all like 2008 in terms of the party spread. How could you be so wrong in 2008 than 2004? And the reason is that 2008 was different than 2004. 2012 will be different than 2008, and in fact, Obama’s not doing as well right now in Ohio, as he did in 2008.
HH: Okay, last question, what percentage do you think Democrats will vote over Republicans in Ohio this year?
LM: Oh, probably about 8 percent, plus or minus three or four.
HH: So it could be four percent?
LM: And it could be twelve.
HH: Okay, I just think, Doc, that’s just stretching it, but I look forward to having you back.
LM: It’s not stretching. That’s statistics and mathematics. I’m not making this stuff up.
HH: No, political science does not suggest that that would be the case, but I hope you come back. We’re out of time, and I appreciate you’re taking the time today.
LM: My pleasure as always.
HH: Thank you, Lee Miringoff of the Marist Institute.
End of interview.