The Pre-Election Roller Coaster

I meant to get this up yesterday but domestic work got in the way so here it is today!

For polling data released during the week of October 19-25, 2008, the partisan weighting targets will be 39.7% Democratic, 33.0% Republican, and 27.3% unaffiliated. For the preceding week, the partisan weighting targets were 39.3% Democratic, 33.0% Republican, and 27.7% unaffiliated.

You have to read the whole thing to understand where they are getting their numbers, but it confirms a lot of what I wrote last Wednesday. However, as I also said last week, these numbers do not take into account the large number of Republicans and Independents who re-registered as Democrats this year in order to take part in the Democrats primaries nor does it take into account the smaller number of Democrats and Independents who registered early on as Republicans to vote in the early Republican primaries.

While Rasmussen does not necessarily take this into account, they do (in a different article) talk about the reasons for the wide array of results in the multitude of polls out there.

At the core of this flap is a polling industry disagreement about the best way to deal with partisan identification in constructing a poll. Just about everyone agrees that party identification is one of the strongest indicators as to how a person will vote. A Republican is overwhelmingly likely to vote for a GOP candidate and a Democrat is overwhelmingly likely to do the opposite.

However, the challenge lies in finding the “right” mix of Republicans, Democrats, and unaffiliated voters. Some pollsters, including many academic and media pollsters, argue that partisan identification is fluid and changes frequently. This approach suggests that whatever partisan mix falls out from the results of a random sample is the “right” answer. In the case of the recent L.A. Times poll, this mix was 39% Democrats and 22% Republicans.

Polls that use this approach tend to produce a more volatile set of results (during Election 2004, one national firm reported results days apart that showed more than a ten-point swing in voter preference).

Others, including most political polling firms and Rasmussen Reports, argue that people rarely change their partisan affiliation (how many people do you know who consider themselves a Republican one day and a Democrat the next?)...

Under normal circumstances, that is a very valid question, but (as we all know) 2008 has been a far from normal year. This election has been a "long strange trip" and it will probably get stranger as we get closer to election day. However, it behooves us all to remember that the polls will only give us a small glimpse of the overall picture. While this glimpse leads us to suspect an overall royal blue picture, it could be that the overall picture is redder (in all the "right" places) than the polls think and that could cause their results to be off badly.

The bottom line is don't take it as a fore gone conclusion - this race is still wide open and with two weeks left (and if Senator Biden is still on the campaign trail) anything could and probably will happen.