Obama's rebound in support. . .

. . .looks a little fishy to me in the latest CBS/New York Times poll. I'm no expert in polling analysis, or anything else for that matter. But, how on earth can you possibly extrapolate a candidate's support among voters from a poll with this kind sample?

This poll was conducted among a random sample of 671 adults nationwide, including 283 Democratic primary voters, interviewed by telephone May 1-3, 2008.

As I said, I'm no expert, but this strikes me as an exercise in meaninglessness.