I'm so glad that Josh Marshall and the folks at TPM captured Chuck Todd's tribute to his boss this afternoon and put it online, because of all the words of tribute spoken today about the late Tim Russert, I found these by far the most moving:
I watched this segment while sitting in my office this afternoon, and afterwards, what I'd been working on suddenly seemed so trivial. I finished up an email, and then headed home a little early to see my family, but especially my young son.
Our condolences to the Russert family and to his colleagues and friends. He will be in all of our thoughts this Father's Day weekend.
This week my colleague Ken Goldstein and I conducted a Wisconsin statewide survey sponsored by the UW Department of Political Science and WisPolitics.com. So fair warning that I'm a party to this survey rather than an independent observer.
A number of people have commented on the party identification balance in the survey: 38% Dem, 24% Rep, 29% Independent (37% Independent when "no preference/other" are allocated to independent. When this group is asked how they "lean", very few insist on some other party, so this allocation makes sense.) See Alan Reifman's blog on weighting and party id for a good example and discussion of broader issues of weighting to party id.
I want to point out two things here and put our data in the context of other polls in Wisconsin.
The chart above shows party identification trends since 2000 using data from three sources that have done frequent polling in the state. What we see is a relatively stable Dem/Rep parity from 2000-2004, with Dem ID falling a bit around 2004 while Reps moved up slightly.
Starting in 2005, however, there is an initially slow but then sharper shift in partisanship. Republican ID declines from about 30% to about 24% today, while Dem ID rises from about 30% to nearly 40%. After an initial surge of independents, that group has recently fallen off a bit. (You have to squint a bit to see WPRI and Badger after 2005, but they are close to the trend lines during this period, so the changes are not just a matter of house effects or phone vs ivr methods. WPRI, for example, has Rep ID moving from 33% in 2004 to 28%, 26% and 25% in 2005-2007. Their Dem ID rises from 30%-33%-34% then falls to 29% over the same period. The final 29% is a large discrepancy from the trend, of course.)
We did not weight our survey to party identification, and these trends help explain why we have reservations about doing that. While relatively stable, party id does move over time, and by a fair bit, as you can see here. But that said, our unweighted results turn out to be quite close to the estimated trends in partisan categories in any case.
The second point is to compare these trends with those in exit poll measures of party id. In 2000, the VNS Exit poll put Wisconsin pid at 37% Dem, 32% Rep and 31% Ind. This shifted in 2004 to 35% Dem, 27% Ind and 38% Rep. But in 2006 the exit polls found that the balance was 38% Dem, 34% Rep and 27% Ind. Those values all show a smaller share of independents at the polls on election day compared to the polling trend, but that is to be expected given differences in turnout between partisans and independents. The size of the party ID groups grows as a result, but the balance between them is in line with what we see in the trends in the polls, though certainly not an exact match. The polls, after all, are of either adults or likely voters, while the exits are by definition a measure of who actually showed up on election day.
For 2006, the Dem exit percent and the Dem trend estimate are a close match. Republicans gain in the exits, by about 6 points over the 2006 trend estimate. If that holds for 2008, we might expect an electorate more like 38% Dem and 30% Rep. Of course both parties will have very active "ground games" and GOTV efforts to try to change those numbers.
While I'm certainly happy that our party id balance is so close to the trend in all the other polling, the more important point is that party id in Wisconsin has shifted quite a bit over the past four years. The coming campaign may alter that, possibly bringing disappointed former Republicans back home, for example. Likewise a Republican advantage in turnout could bring the exit polls back to closer balance. But as the data show, today the GOP is at the worst disadvantage the state has seen in over eight years.
Let me conclude with a bit of description of the polls used here.
Wisconsin Policy Research Institute ("WPRI") has done some of the longest running polls in the state, usually two a year. Their data here is taken from their annual estimates, which I assume pool the two surveys though they don't say so explicitly. WPRI describes itself as "Wisconsin's Free Market Think Tank".
The "Badger Poll" is conducted by the UW Survey Center. They did more extensive polling in 2002-04 but now do about two polls a year.
SurveyUSA is a well known national pollster that uses "Interactive Voice Response" (IVR) automated interviews. SurveyUSA has done monthly polling in the state since 2005, providing some of the best data on state trends in approval of elected officials and as a byproduct have an excellent data series of party ID.
Finally, there is our new Department of Political Science/WisPolitics poll. Ours uses a commercial call center, not the UW Survey Center or undergrads in a class calling for a grade. WPRI, Badger and our poll all use live interviewers, SurveyUSA uses IVR. Most of these surveys are in the 500-600 respondent range.
One critique that many commentators had of Clinton and her relationship with Mark Penn was that it might have been a bad idea to have only one pollster and have that person serve as chief strategist. I read the Obama team has four. But, I was wondering, what's conventional as far as number of pollsters in a campaign. Obviously, it would vary in different kinds of races.
Let's start with that last point. Presidential campaigns, and especially the Obama and Clinton campaigns of 2008, belong in their own special category of "normal." Most campaigns for Senate, Governor or Congress hire only one manager, one pollster, one media consultant because that is all they can afford. Presidential campaigns also have unique challenge of needing to poll in many states at once. For the general election, for example, you can assume that both campaigns will conduct internal benchmark surveys between now and Labor Day in 30 to 40 states, and will likely conduct ongoing tracking programs in at least 20 during the fall campaign.
That is a lot of work, and so the multi-poll structure of the Obama campaign is not unusual. Back in 1992, Stan Greenberg was the lead pollster for Bill Clinton's campaign for president, but he invited four more Democratic firms to conduct surveys in various general election battleground states. Among those was the firm formerly known as Bennett, Petts and Blumenthal (although technically, my name did not go on the door until 1995).
Speaking of which, the Obama campaign is now up to six pollsters, not just four, including my former business partner Anna Bennett. As The Washington Post's Chris Cillizza reports, the Obama campaign is dividing up their advertising, polling and direct mail efforts into six teams:
On the polling front, the changes are more marginal, as Obama had already been using five different firms to conduct the massive amount of survey research required during the protracted primary fight.
Cornell Belcher (Brilliant Corners), Joel Benenson (Benenson Strategy Group), Paul Harstad (Harstad Strategic Research), David Binder (David Binder Research) and Anna Bennett (Bennett Petts & Normington) will all continue to do polling for the campaign. The new addition is John Anzalone (Anzalone Liszt Research), a rising star in the political polling world who has wins in two southern House special elections -- Louisiana's 6th and Mississippi's 1st -- under his belt already this year.
And in fairness, Hillary Clinton's campaign also involved more pollsters than just Mark Penn. Although they famously demoted Penn and promoted Geoff Garin (of the Garin Hart Yang Research Group), Garin had been brought on board already, along with Diane Feldman (The Feldman Group) and Sergio Bendixen (Bendixen and Associates), to assist with the crush of polling needed for February 5 and beyond.
But to come back to the gist of the reader's question, the Obama campaign's relationship with its pollsters and other consultants does appear to be different than Clinton's, even if the contrast is less about the head count than about philosophy. Consider these comments from Penn himself, in the lengthy GQ interview that has had the blogosphereabuzzforthelast24hours:
Okay, but specifically. What are the one or two or three things that you wish you’d done differently?
I wish in reality that I had a team of people, you know, who was with me, that I organized, as I had in ’96. Look, remember, a big difference between me and a lot of people is that I’ve been doing this for thirty years. I’ve run the successful strategy of a presidential campaign in ’96. I’ve run overseas campaigns like Tony Blair’s and, you know, been through this on the big scale. And in ’96, I had a close-knit team that really ran everything. And this was not organized that way.
Why couldn’t you bring your team this time?
I think this was organized in a way which, you know, some people think is a better organization—to have, instead of a team, almost a group of rivals. And you know, one would say, overall it worked pretty well. Till October.
By contrast, all reports say the Obama team has lived up to the "no drama" mandate set early on by the candidate. In fact, as Chris Cillizza reported, the fact that none of the new names added by Obama in recent weeks leaked, despite weeks of ongoing interviews, "is a sign of the level of discipline the campaign demands." Cillizza also adds this bit of context, which is easily overlooked:
Splitting the media consultants [and pollsters] into teams focused on specific regions is an idea borrowed from the structure used to great effect in the last few cycles by the Democratic Congressional Campaign Committee and the Democratic Senatorial Campaign Committee. The goal of such an approach is to take full advantage of the knowledge about a particular state or region accrued by a consultant or group of consultants over a series of past campaigns.
I can add that from what I hear, the DCCC/DSCC team approach that has quietly taken hold over the last two election cycles has made for far less "drama" and more teamwork than in prior years.
My NationalJournal.com column, on the utility of national polls now that our attention is turning to the state-by-state electoral college battle, is now online.
As I was writing it, Nate Silver posted an observation that may be a bit contra-theory:
There have now been six [state level] polls that were in the field since the Democratic primaries were concluded, and for which we have a previous trendline against which to compare. Barack Obama has gained ground in all six of those polls; his average bounce has been about 5 points.
We also have new surveys this morning showing Obama with significant leads in New Jersey (by Quinnipiac University) and Wisconsin (by the University of Wisconsin and WisPolitics.com and our own Charles Franklin). Still the first clear sign of an post primary Obama bounce came from the national tracking surveys.
For statistical modelers, number crunchers and turnout scholars among our readers -- and you know who you are -- Chuck Todd and the crew at the NBC News political unit have thrown down the gauntlet:
*** Analyzing the turnout: After crunching numbers for the last several months during the Clinton-Obama contest, we’ve been experiencing mathematical withdrawals now that the Dem race is over. In a word, we have the shakes. So to calm our nerves, we got out our abacuses and did some initial fooling around with projected popular vote. Using the 2004 results as a baseline, we were curious as to which states would swing to Obama if he does raise overall turnout by 20% (approximately another 22 million voters) and wins those new voters by a 60%-40% split. Assuming an even distribution -- which we know is potentially a flaw in this estimate, so back off! -- a 20% turnout increase breaking 60%-40% for Obama would swing four states from red to blue (Iowa, New Mexico, Nevada, and Ohio). If Obama wins the new voters by a 65%-35% margin, two more states come over (Colorado and Florida), with another (Virginia) essentially too close too call. We're going to crunch these numbers a number of ways over the next few weeks, including using the 2000 election as our baseline (since many folks believe 2004 over-estimates the GOP electorate); seeing what would happen if Obama runs a 50-state campaign but McCain runs a 17-state one; and finding out what the realistic maximum population vote advantage Obama could have while losing the electoral college. In the meantime, have fun with this model.
Thoughts anyone? Alternative models or analysis? Post a comment or email it our way (questions at pollster dot com).
The release of the latest national poll from CNN/Opinion Research Corporation featured a question that included Ralph Nader and Bob Barr as, respectively, independent an Libertarian candidates for president. The fact that Nader received 6% of the vote among the 921 registered voters interviewed surprised and intrigued many of our readers.
I went back to the data collected by RealClearPolitics at this point four years ago and discovered that Ralph Nader received an average of 5% of the vote (and a range of 3% to 7%) on national surveys fielded during the first half of June 2004:
CNN's latest survey included two CNN asked two versions of the presidential vote question. The first offered just McCain and Obama as choices, the second included Nader and Barr:
If Barack Obama were the Democratic Party's candidate and John McCain were the Republican Party's candidate, who would you be more likely to vote for -- Obama, the Democrat, or McCain, the Republican? (IF UNSURE:) As of today, who do you lean more toward?
Now suppose that the presidential candidates on the ballot in your state included Barack Obama as the Democratic Party's candidate, John McCain as the Republican candidate, Bob Barr as the Libertarian party candidate, and Ralph Nader as an independent candidate, who would you be more likely to vote for? (IF UNSURE:) As of today, who do you lean more toward?
One of my first thoughts on seeing the latest results is whether the order of questions -- asking the four-candidate question second -- might help produce more apparent support for Nader and Barr. Many of the links from 2004 have long since gone dead (so our ability to track down full questionnaires is limited). However, the Pew Research Center poll from four years ago also produced a slightly larger than average Nader vote, and that survey asked their three-way candidate choice question first.
We will keep close watch on the various forms of the presidential vote questions that pollsters ask over the next few months. At the state level, we will eventually see pollsters ask vote preference questions that match the names on the ballot, although most will try to limit choices to the better known alternatives. At the national level, we may start to see more pollsters following CNN's example and asking two versions of the vote question. In such cases, our general rule is to use the first question asked as the result of record for Pollster.com's charts and tables. However, if enough pollsters start asking two forms of the question, we may create a separate charts and tables to track each.
Last Friday's New York Times included an op-ed column by Neil deGrasse Tyson, an author and astrophysicist who used current polling state-by-state polls to conclude that "if the general election were held today, Barack Obama would lose to John McCain, while Mr. McCain would lose to Mrs. Clinton."
His assertion depended on "a new method of analysis on the statistics of polls" developed by two astrophysicists, J. Richard Gott III and Wes Colley, "that has been accepted for publication in the journal Mathematical and Computer Modeling."
Here is the gist of their method:
[I]n swing states, the median result of all the polls conducted in the weeks prior to an election is an especially effective predictor of which candidate will win that election — even in states where the polls consistently fall within the margin of error.
So the idea is this: Ignore sampling error and award states to the candidates if they are "ahead" (even by a single percentage point) in a greater number of polls. That method may work out roughly the same as an average in a state with a large number of polls. Tyson does not say how many polls the Gott-Colley method used in each state in 2004, but in that year the Kerry-Bush results remained reasonably stable over time (so counting up all polls over a 2-3 month period may have worked as well as watching the final week). Moreover, you could have skipped the "rocket science" in 2004 and just examined the final RealClearPolitics averages. The candidate leading on their final averages won every state except Wisconsin.
However, apply that counting method to the "past six weeks of polls," as Tyson did, and you run into a problem: Very few polls, so the counting method starts to break down. Thus, for the crucial 20 electoral votes available in the state of Ohio, Tyson tells us:
In Ohio, for example, Mr. McCain beats Mr. Obama two polls to one. But Mrs. Clinton beats Mr. McCain two polls to nothing. So Ohio, which Mr. Kerry did not win in 2004, would go into Mrs. Clinton’s column, giving her an additional 20 electoral votes.
Shazam! That's not a "two to one" margin, that's three polls, total: One (from SurveyUSA) showing Obama leading by 9, one from Quinnipiac University showing McCain leading by 4, and the tie-breaker from Rasmussen Reports showing McCain with a single percentage point advantage. Never mind that if you average the three (as RealClearPolitics does), they give Obama with a one-point advantage. Or if you draw a regression line through all the available polls -- as we do -- you get a the same one-point Obama edge. Altogether, these data suggest a very close race in Ohio, as of mid-May, not a clear leader. But never mind all that. Tyson applies the Gott-Colley procedure and gives the state to McCain.
The bigger problem with the Tyson column is is the phrase, "if the general election were held today." It isn't. The notion that polls are just a "snapshot" of opinion may be a hackneyed cliche, but it is nonetheless true. The current batch of horse-race polls tell us about voter preferences over the last six weeks. The next six weeks may be different.
Andrew Gelman reproduced a chart from a paper he co-authored 15 years ago to remind us all that polls conducted five or six months before an presidential election are often poor predictors of the final outcome (h/t Monkey Cage):