48% of everyone reading this won't care...

As I write this, the Harris poll is showing 48% Kerry, 47% Bush; Pew shows a 46%-46% tie; Gallup shows 55% Bush, 42% Kerry. What the f@$#%?!?!?!?!?!

If you are anything like me, you have been obsessing over every single poll that comes out during this highly charged political season. For the sake of your sanity, I hope you are not. These polls can drive the most passive observer to fits of rage and hair-pulling. Some of them come out and show the presidential election in a dead heat, while others declare Bush up by huge points. That is quite a disconnect and it's very disheartening when the cable news networks only tout the polls that show a wide margin between candidates. It's the lazy, "let's get this over with" reporting style of the major news companies. A poll stating how close the race is isn't very new. A poll showing an incredible surge for the incumbent however is something new and different. Too bad it's also deeply flawed.

The polls (Newsweek, Time, Gallup) that show a commanding lead for our uncommanding commander-in-chief use a methodology of partisan identification that heavily favors republicans. The sample of people they poll breaks down as 38% Republicans, 31% Democrats, and 31% Independents. By asking a huge margin more of Republicans how they would vote because pollsters have arbitrarily decided that more Republicans will come out to vote is not only misleading, it is against actual information. In the last 2 presidential elections, Democrats have shown up more at the polls than Republicans 39%-35%. So why count more Republicans this time? Doesn't make any sense. But if you weight the data in these types of polls, then the results correct themselves and they show a dead heat.

The new CBS News/New York Times poll, conducted September 12-16, gives Bush an 8 point lead (50-42) among RVs--but also gives the Republicans a 4 point edge on party ID. Reweight their data to conform to an underlying Democratic 4 point edge (using the 39D/35R/26I distribution from the 2000 exit poll) and you get a nearly even race, 47% Bush, 46% Kerry.

Nearly even. That goes along with the 46%-46% tie in the Pew Research Center poll (which gave the Democrats a 4 point edge on party ID without weighting) and the 48%-48% tie in the Gallup poll (once weighted to reflect an underlying Democratic 4 point edge). Not to mention the two other recent national polls (Harris, Democracy Corps) that show the race within one point.

Perhaps all this is just a coincidence, but the pattern seems striking. Once you adjust for the apparent overrepresentation of Republican identifiers in some samples, the polls all seem to be saying the same thing: the race is a tie or very close to it.

Though I still can't see how Bush can even be considered a viable candidate by half the country.