Polls that mislead

The front-page headline in today’s Washington Post proclaims: “Poll Shows Strong Shift Of Support to Democrats.” The poll in question is by the Washington Post/ABC News. A New York Times/CBS poll purports to show the same phenomenon.
Bull Dog Pundit isn’t buying it. He argues that both polls fail properly to sample the voting electorate, and are being used to “drive” the news. It appears that about half of those sampled by the Times either aren’t registered to vote or didn’t vote in the last midterm election. The poll also oversamples Democrats and Kerry voters, although not by that much.
In the Washington Post poll, the oversampling of Democrats seems significant — Dems outnumber Republicans by 11% (38-27%). Moreover, 3 of the 4 nights in the WP poll are weekends. According to Bull Dog Pundit, the poll director at the Post has previously admitted that weekend polls favor Democrats.
I’m not claiming that the Democrats haven’t gained a bit lately, and I continue to believe that this is going to be a bad year for Republicans. But I don’t base these views to any degree on the two polls in question.

Notice: All comments are subject to moderation. Our comments are intended to be a forum for civil discourse bearing on the subject under discussion. Commenters who stray beyond the bounds of civility or employ what we deem gratuitous vulgarity in a comment — including, but not limited to, “s***,” “f***,” “a*******,” or one of their many variants — will be banned without further notice in the sole discretion of the site moderator.

Responses