When it comes to polls and pollsters: Illegitimi non carborundum

Jay Cost at Real Clear Politics uses some fancy math to show how bizarre this year's polls are, and in particular how much they're contradicting each other, as compared to previous years' polls. Don't let any of 'em get you down, I argued in a guest-post at HughHewitt.com on Friday.

---------------------------------

[Copied here for archival purposes on November 5, 2008, from the post linked above at HughHewitt.com.]

(Guest Post by Bill Dyer a/k/a Beldar)

I'm once again going to deviate from my normal disinclination to discuss polls, but it's only to bring you what I think is a well-informed and clear-eyed warning about the current polls you're reading. From Jay Cost at Real Clear Politics, based on his careful and comprehensive analysis of a wide range of current political opinion polls:

So, we have made three observations: (a) relative to 2004, the standard deviation for Obama and McCain's polls are high, indicating more disagreement among pollsters at a similar point in this cycle; (b) the shape of the distribution of each candidate's poll position is not what we might expect; (c) multiple polls are separated from the RCP average by statistically significant differences.

Combined, these considerations suggest that this variation cannot be chalked up to typical statistical "noise." Instead, it is more likely that pollsters are disagreeing with each other in their sampling methodologies. In other words, different pollsters have different "visions" of what the electorate will look like on November 4th, and these visions are affecting their results.

Mr. Cost insists that he's "not making any claims about which pollster has the better sample of the electorate," and further insists that he "frankly [does] not know" whether the polls showing an Obama blowout or the polls showing a close race are more accurate. But somebody is going to be proved by the election results to have been horribly, horribly wrong in their late October polling.

I don't have Mr. Cost's expertise, nor his incentive to avoid labeling any particular pollsters as fools, but I do have some common sense. And my common sense suggests to me that the pollsters who may be having over-dramatic and unrealistic "'visons' of the electorate" are more likely to be those who also are philosophically inclined to want and believe in the election of the candidate of unproven hopey-changiness. (Never mind the skew that might result from the fact that if a pollster dares to report a poll that's encouraging to McCain-Palin, he'll promptly get death threats by email.)

My advice, then, for conservatives who are encountering feelings of dismay right now: Illegitimi non carborundum. Don't give up; don't quit; don't be dismayed.

Liberals: Go ahead and party like it's 1996!

— Beldar