The Central Problem in the Polling Debate?

Too many people ignore (and incorrectly define) the "independents" in a given sample.

As I continue to argue in various comment threads and read various pieces on polling it becomes increasingly clear that there is simply a profound misunderstanding of what “independent” means and, by extension, what that partisan breakdown of a given poll may mean.  Each poll tends to have a percentage of the respondents who identify as Democratic, a percentage who identity as Republican, and a percentage who identify as independent.  Many times the Democratic number is higher than the Republicans number (and hence the complaints about skewing in the direction of Democrats).

First, most pollsters simply ask how the respondents identify, they do not adjust the sample for a pre-determined partisan mix.  As such, a given partisan breakdown is a reflection of the sample, not of the preferences of the pollster.

Second, in national polling, there is a consistent pro-Democratic partisan ID in poll after poll (see Gallup or this post from Chris Cillizza which details numbers from various sources). This is not because the pollsters are weighing the poll, it is because that is how respondents self-identify (note the word “self”).  As such, there are strong empirical reasons to expect any given national sample to have more self-identified Democrats in it, and this is true for a lot of state level polls as well.

Third, “independents” are not independent in the sense that that they can go either way.  It is simply how those people choose to identify themselves.  Almost all of these people are “leaners” who normally vote D or R.  And, in recent years, there are data to suggest that more and more people who tend to vote Republican have been identifying as “independents.”  This has been the trend since the end of the first Bush term (and, no doubt, views of Bush have played into people not wanting to identify with the GOP as a result).  Note the following  from the Pew Research Center (as provided by Cillizza):

Consider:  a poll in 2008 that reflected the above would have had a 38 D, 28 R, and 29 I (a dreaded +10 D skew, but also with 29% not accounted for) and yet Obama won in 2008  53%-46% (a 7 point differential and only 1% going to others).  Hence, a lot of those independents eventually voted Republican as 46 is quite a bit higher than 28.

In short:  the actual partisan preferences in a given poll are obscured by the fact that a given person being polled can simultaneously be a heavy leaner (or, in fact, a dedicated, long-term Republican or Democrat) and still call oneself an “independent.”

Look at the graph above for 2012:  33% identify as independent and only 28% as Republican, yet we all know that a huge chunk of those so-called independents will vote Republican (and a huge, but smaller, chunk will vote Democratic).  This also means that when we see numbers that tell us that Romney is doing better with independents than is Obama that we should not be surprised.  Indeed, that is what we should expect to happen.  Consider:  if we take the RCP average at the moment shows 47.7 for Romney and 46.3 for Obama.  Based on the graph above, (and assuming, for the sake of argument that all Rs go Romney and all Ds go Obama, which will not the be case) that would mean that the Ds are getting roughly 12 of the 33 points associated with independents and the Rs are getting about 21.  This illustrates that more Republican voters are calling themselves independents than are Democratic voters.

As I noted in a comment yesterday, the best indicator in all these polls as to the true R/D breakdown in the sample (as it pertains to voting, which is what matters) is how they answer the Obama v. Romney question, not their partisan self-ID (which is not a demographic characteristic that remains static the way race and gender do). All of the +X D business is really missing the point about what the numbers, especially the Independent numbers mean.

This is not to say that the polls can’t be wrong, but it is to point out that one cannot look at a threeway breakdown of partisan-ID and then only compare two of those numbers.

FILED UNDER: 2012 Election, US Politics, ,
Steven L. Taylor
About Steven L. Taylor
Steven L. Taylor is a Professor of Political Science and a College of Arts and Sciences Dean. His main areas of expertise include parties, elections, and the institutional design of democracies. His most recent book is the co-authored A Different Democracy: American Government in a 31-Country Perspective. He earned his Ph.D. from the University of Texas and his BA from the University of California, Irvine. He has been blogging since 2003 (originally at the now defunct Poliblog). Follow Steven on Twitter


  1. Koda says:

    Scott Rasmussen explained this to the conservative base at the height of the “skewed polls” bullshit, and not a single one of them listened. They’re completely impervious.

  2. al-Ameda says:

    Well, that chart tells me that for years the number of “Independents” has been grossly overstated.

    This is probably because there is some tendency to want to tell pollsters that one is “independent.” It sounds better to say you’re “independent” because that implies that you’re somehow more objective, rational and reasonable than a person who says that he or she is a Democrat or a Republican.

  3. john personna says:

    I think your poll analysis is fine, but I think your conjecture about the motivations of self-identified independents is unnecessary to the argument.

    Randomly selected voter Bob tells you that he’s going with Romney. Given a large enough sample size, that’s all you need to tally Romney’s current popularity. That he is a self-identified independent is secondary data.

    Now as far as this lean stuff, I’m still skeptical. What are you going to do, track Bob for 20 years to see how consistent he is? To make sure he always votes economics over social issues? It would probably take that long, and in that time, Bob might have changed.

  4. john personna says:


    Partisans endorse a platform.

    Anyone who cannot support any party platform, as they stand today, should identify independent.

  5. Koda says:

    @john personna: You don’t have to track Bob for 20 years. It’s a lot easier than that. They just ask people who they voted for in previous elections. And it’s not at all uncommon to see that asked.

    As noted in the article, almost all independents vote for one party consistently. There are a fairly small number of people who regularly swap from one party to another.

    As for the necessity of this all, people keep conflating independents, swing voters, and undecided voters. They’re not all the same, and I wish people would stop treating them as such. They probably won’t though. Especially not the conservative base, which has now decided to add statistics to their ever growing list of things they reject as elitist.

  6. al-Ameda says:

    @john personna:

    Partisans endorse a platform.
    Anyone who cannot support any party platform, as they stand today, should identify independent.

    I’m a Democrat, and of course I do not endorse everything that’s in the party platform, but so what?

    In fact, I probably support many ideas (more nuclear energy, less regulation, pull back on Sarbanes-Oxley for example) that many Democrats consider to be Republican oriented. Yet it is highly unlikely that I will vote for a Republican for a House or Senate slot because by doing so I’m not going to get the Olympia Snowe types, I’m going to get the James Inhofes and Steve Kings. So I’m not going to support or enable that.

  7. MBunge says:

    @john personna: “Partisans endorse a platform.”

    Without platforms, there are no political parties. It’s just anarchy.

    Here’s the problem. If you’re going to be an independent and eschew the cues or guidance of a political party, you carry a greater responsibility to inform and educate yourself on the policies and, frankly, intellectual and moral standing of the candidates to which you vote and the parties to which they belong. I don’t think there’s any evidence that independents are fulfilling that duty.


  8. It should be remembered as well that party ID often driven by local factors, including closed primaries and the ability to vote to influence local outcomes.

    Party ID is complicated and goes beyond party platform adherence, especially in a federal, separation of powers system.

  9. rudderpedals says:

    Invert the affiliation plot’s GOP trace – the fit with the independent trace is cool. It’s Affiliation Tectonics!

    Do actual campaigns specify declared affiliation data when they place an order for an internal-use poll?

  10. al-Ameda says:

    @Steven L. Taylor:

    Party ID is complicated and goes beyond party platform adherence, especially in a federal, separation of powers system.

    At the very local level, party affiliation rarely matters, around here it’s all about land use issues. And the divide is not Republican/Democratic, it is based on very low growth and no growth, or strongly environmentalist (green) or mainstream environmentalist. Democrat and Republican do not come into play at all.

  11. @al-Ameda: It depends on where one lives. Closed primary states with one party dominance (e.g., DC) can lead Reps to register as Dems so as to have an influence on outcomes.

    In the South, up and until recently, it was quite complex (and still has some weird very local permutations).

  12. Plus there is the fact that we know some Congressional districts go D for pres and R for congress and vice versa.

  13. LC says:

    Actually what bothers me more is the low response rate, about 10%. That is so low that there almost has to be something different about the people who respond to the polls vs. those who don’t, and I don’t think we have any real idea who they are or how they are different. This makes the weighting of the responses in the individual polls all that more important. And I don’t think anybody knows whether the weights that are being applied are reasonable.

    We’re all just assuming that since all the pollsters probably use different weighting protocols, if they all come out with close to the same numbers, there probably is no problem.

  14. KansasMom says:

    @Steven L. Taylor: I’m the most liberal Republican in Kansas because everything is decided at the primary level. I either vote for the most rational one, for the sake of future governance or the craziest one, assuming they have a a good Democratic opponent. Lately the crazy has gotten so strong that it hasn’t mattered. We will be the Koch inspired experiment for the nation to learn from.

  15. michael reynolds says:

    @john personna:

    Randomly selected voter Bob

    I’m sick of Bob. Fwck you, Bob!

  16. Janis Gore says:

    @Steven L. Taylor: It can get very complex in the south.

    Some few years ago, when FIL was still alive, he wanted everyone in Louisiana to vote for his cousins’s son, who was running for a state office.

    No buddy, not so fast. The guy owns a funeral home and the very first thing on his mind would be making that process as elaborate and expensive as possible through regulation.

    Man wasn’t in business for anybody’s health.

  17. Janis Gore says:

    The candidate self-identified as a Republican.

    Independent since 1976, for me.

  18. john personna says:

    There are 100+ million people registered to vote in the US. There are two main parties.

    The audacity here is to think that a binary choice is an appropriate to understand 100+ million people. Certainly some in those millions will like one of the two platforms well enough to sign on, and will defer to guidance from people with that platform, but it is a rude tool.

    Given the two choices though, some people say they don’t like what’s offered and think themselves independent.

    Should they really be told that no, a single scale is all you need, and all 100+ million can be Republican, or Democrat, or lean that way?

    I really hope to hell not, and I hope that political scientists, if they are serious, can work out something a little more sophisticated. They should have something with many divisions. Not two. Or “lean two.”

    Because if you start forcing things to a single choice you become, by definition, reductionist. That suits the parties of course, because they gain pseudo members by lean. It makes elections simpler because you don’t need to worry about people’s actual preferences. You can just go with their vote in the last election.

  19. Lomax says:

    “Polling” was invented by a psychologist who had done behavioral research on lab animals and then moved it up to – people! Polling is a way of controlling behavior and brainwashing people. Debates and polling: just two more ways that the “election” is controlled and already programmed!

  20. MBunge says:

    @john personna: “Given the two choices though, some people say they don’t like what’s offered and think themselves independent.”

    Why are they saying that, though? There are a lot of third parties out there and none seem to have benefited at all from the rise of the so-called Independent voter. If voter independence is a form of narcissism, “no one’s good enough for me”, I’m not sure that’s something that can or should be reflected in our political structure.


  21. john personna says:


    Well, how do you conceptualize which came first, voters or parties?

    If you think parties are fundamental, that the two party system we have is fundamental, then people must aggregate themselves into the two basic types.

    I think if you start with people first, you go the other way. There are 100+ million voters out there, and there are two organizations which compete to attract them. They devise platform not based on a platonic ideal, but on population dynamics of the moment.

    In that later model the two party system is a static self-replicating pattern, nothing more.

    Put another way, it reduces to the old joke. There are two kinds of people in the world: people who think there are, and people who don’t.

  22. john personna says:

    I should say “persistent self-replicating pattern”

  23. MBunge says:

    @john personna: “Well, how do you conceptualize which came first, voters or parties?”

    Voters, of course,but voters that used to be much more comfortable participating in politics through the two established parties. The issue is what has disrupted that “persistent self-replicating pattern”. Has the two-party dynamic and structure outlived its usefulness? Or are voters defecting from it for reasons that are non-rational?

    For example, how many independents are really “independent” and how many are fairly reliable Dem or Rep partisans who, for reasons of self-image or what have you, prefer to not specifically identify with the group to which they politically belong?


  24. john personna says:


    The argument for parties is that a group with common cause is stronger in politics than disorganized individuals. So it is natural for people with a common cause to choose aggregate.

    What we are talking about here though is some attempt to rope in people who don’t believe they have that common cause. To “identify” them as included anyway.

    We don’t rope them into 5 or 6 parties just because we don’t have 5 or 6 strong parties in the US. Because we just happen to have 2, we see people “assigned” to 2.

  25. MBunge says:

    @john personna: “What we are talking about here though is some attempt to rope in people who don’t believe they have that common cause.”

    Is that belief in a lack of common cause, though, intelligent and rational? Are there people who don’t care about the environment? Health care? Education? War? Peace?

    If voters are fleeing two-party identification for non-rational reasons, that’s not a problem with the two-party structure. It’s a problem with the voters and the culture in which they reside and won’t be fixed by having more or fewer parties from which to choose.