Both Pew and Mystery Pollster, who is actually Democrat Mark Blumenthal, make the same argument about Party ID. Specifically, they claim Party ID is an attitude, not a demographic, and thus is not something a poll should be weighted by. In fact, their phrasing on this matter is remarkably similar: Does this come from some sort of polling handbook or something? Besides, and even though this is not the point, they are wrong. Race is changing all the time as a result of shifting definitions. Further, and this is an unfortunate reality, age is always changing. In this election cycle alone, I went from being in the 18-29 demographic in the primaries to the 30-44 demographic in the general. Anyway, that's not the point.

Instead, after reading through the data presented by both Pew and Blumenthal, and I have come to agree with them, but only in part. Independent Party ID is an attitude. By contrast, Party ID among Democrats and Republicans is remarkably stable and does constitute a demographic. Almost all of the shifts caused in Democratic and Republican Party ID is caused by independents either shifting to one major party, or shifting away from one major Party back toward independent. For example, here is the chart Pew produced to argue that Party ID is unstable:

The change is not taking place among Democrats and Republicans. Instead, the change is taking place within two groups of voters, "Independent Democrats" and "Independent Republicans," that a three-way Party ID question is unable to measure. According to the chart that Pew produces to argue that Party ID is not stable, what they end up instead proving is that "independents" when considered as a block, are unstable. Of the 16% they identify as changing Party ID from October 23-26, 1988 until November 9-11, 1988, 15% were changing from independent to one of the two parties or from one of the two parties to independent. Only 1% of the people questioned shifted from one party to the other.

Pew's 1992 and 2000 graphs show similar lack of movement among partisans. From June 1992 until November 1992, only 4% of the population shifted from one party to the other, while 22% shifted from independent to one major party or from one major party to independent. In 2000, only 2% shifted from one major party to the other, while 18% shifted either from one major party to independent or from independent to one of the major parties.

Mystery Pollster goes on to cite the 2000 National Annenberg Election survey, through a book entitled Capturing Campaign Dynamics, which was written by the NAES 2000 team. Blumenthal write (emphasis in original):

The conclusion that NAES made from this was that Independent Party ID "was not stable over time."

Fine. Independent Party ID is not stable over time. Pew demonstrates the same. However, at the same time there is no evidence of any significant shift from Democrats to Republicans or vice-versa. Democrats are not becoming Republicans and Republicans are not becoming Democrats. Even the data used to argue that Party ID is an attitude and not a demographic demonstrates that almost every change in Democratic and Republican Party ID occurred as a result of Independents shifting one way or the other.

One could stop at this point and assume that Party ID is stable among partisans, but not among Independents. However, this would be wrong, since the shift these polls are measuring among Independents is a mirage generated by a three-way Party ID question in what is at least a five-way Party ID country. Specifically, what most polls ignore is that while around 40% of the population consider themselves to be "Independents," around 75% of Independents lean toward one party or the other and can be accurately considered "Independent Democrats" or "Independent Republicans". However, by forcing those two groups of leaners to choose between their two allegiances, especially in a dataset of 1,500 or less, the three-way question, and possibly wavering base energy, will create the appearance of a shift that has not taken place.

If polling firms were to instead use the University of Michigan's seven-point scale, the long term of stability, and only glacial movement, of Party ID would come into clearer focus. (I can't reproduce the chart here, so please click on the link). According to this chart, there was one long-term trend, erosion in Democratic Party ID, lasting from roughly 1960-1984. Not coincidentally, this was also the period that saw the collapse of the New Deal Coalition. As the state-by-state Partisan index chart on the President 2004 page shows, that collapse was completed in 1984 as the entire South shifted heavily against where they stood in 1976 and 1980 and never went back.

However, since that collapse became final, while there has been virtually no actual movement in overall Party ID between the two parties, there has been is a fairly regular shift within Democratic and Republican ID groups. While the number of total Democrats from 1984-2002 has never been outsdie the 47% to 51% range, there is almost constant fluctuation in the number of Strong Democrats, Weak Democrats, and Independent Democrats. From 1984-2000, the total number of Republicans never varied outside of the 36-41% range, but the number of Strong Republicans, Weak Republicans and Independent Republicans varied quite consistently. While 2002 shows a possible Republican rise in Party ID, a rise that was registered in other 2001-2003 Party ID surveys such as Pew, in 2004 those same surveys have seen that temporary change revert to pre-9/111 levels. It would be helpful if Michigan would release its 2004 numbers, in order to see if their results agree.

What the Pew, NAES and Michigan data all suggest is not unstable Party ID across the board, but instability within groups that all identify with a particular party. Specifically, these polls reveal that the way "Independent Democrats" and "Independent Republicans" choose to identify when forced into a three-way cookie cutter question can fluctuate significantly, especially when faced with small datasets. The unmeasured "Independent Republican" and "Independent Democrat" would both be very small in the Pew datasets in particular.

Not all Independents are created equally. In fact, the vast majority of them actually do favor one party over the other, as both Michigan and, even Pew, show. However, because almost every survey only measures by three-way Party ID, there is no way to know if they are including the right sort of Independents in their polling sample. "Independent Democrats" are very different from "Independent Republicans" and both are very different from "Independent Independents." A poll that contains too many or too few of one kind will have inaccurate results.

What is particularly frustrating about this is that Pew knows good and well that these nominally Independent "party leaners" exist, but they do not poll for them in their trail heat surveys:

In other words:

• First, Pew releases a study that shows a significant majority of Independents lean toward one party or the other. These people are, in Michigan's terminology, "Independent Democrats" or "Independent Republicans."

• Pew releases a chart showing that shifts in overall Party ID are almost entirely accounted for by a group of people shifting either to or from "Generic Independent" to "Generic Major Party." By contrast, according to their own study, a miniscule percentage of people shift directly from Democrat to Republican or vice versa.

• Yet, despite this, Pew does not acknowledge that the shift in Party ID that they measure are very likely caused by "Independent Leaners" shifting from their party to their Independence from one day to the next.

I think that there is strong evidence to suggest that what takes place during Party ID shifts is caused by the question, not by "attitude." Considering this, I maintain that it is entirely possible to weight by Party ID, as long as Party ID is being measured accurately. It will simply be necessary to push the party leaners into their Party, and truly separate Democrats, Republicans and Independents from one another.

What does this says about polling in this cycle? First, it is important to remember that re-weighting most recent polls by Party ID of late hasn't caused any real change in their results. Fox, Marist, and ABC don't change at all. The LA Times, Pew, and CBS, only see small shifts of four points or less total between the two candidates, well within the margin for error. Truthfully, only Gallup and, to a lesser extent, Time, reveal noticeable shifts upon re-weighting. Further, even considering the Party ID numbers I have gone through in this entire essay, Gallup's Party ID numbers are still clearly a crock. A 40%+ Republican ID would require nearly every single "Independent Republican" to identify as a Republican, while a Democratic ID in the low thirties would require a large percentage, if not all, "Independent Democrats" to identify as "Independent." If this is what was really happening, Kerry would be crushing Bush among Indies in the Gallup poll, probably by 20-30 points.

Overall, what I think this tells us about polling is, basically, that we lack adequate information to know how accurate polls are in terms of Party ID (unless, like Gallup, there is an extreme outlier). Both previous exit polls from previous elections and typical Party ID poll internals are inaccurate measurements of Party ID because they use the three-way question without pushing the Independents. Re-weighting polls by Party ID from exit polls doesn't clearly make things worse, but it certainly doesn't make them better either. You either need a question with more options, or you need to push the Indies to choose. I'd accept Party ID weighting if accurate information of that sort was available.

More importantly, what I think this shows is the folly of trying to appeal to independent voters as a campaign tactic, instead of consolidating and energizing your base. There just are not many "Independent Independents" out there (maybe a little than 10% of the registered voter population), and they don't vote very often anyway. I wouldn't be surprised if "Independent Independents" make up only 6-7% of the vote in national elections. Why bother spending so much time appealing to such a small group when keeping your base intact is far, far more important?

Howard Dean may have had some image problems, but at least he had the right strategy: appeal to the base. Register the base. Energize the base. Consolidate the base. This is especially true for Democrats, who have a larger base than Republicans. Our problem has historically not been with independents, but with not holding our own base together and with turning out at a lower rate than Republicans. When has Democratic turnout ever equaled Republican turnout? When has a Democratic nominee ever held his base together as well as the Republican nominee? 1964 is probably the last election that meets both criteria.

Howard Dean had it right, and Karl Rove has it right as well. Woe be unto us if we continue to mock the way Bush is only going after his base, while Kerry seeks "swing voters." Bush has a solid strategy, but I worry that Kerry has been chasing a mythical beast.