The latest @CBSNews/@nytimes poll is suspect.

There's a massive selection bias in this poll:

Romney 46
Obama 43

Why do I say that there's a selection bias? Because:

This poll was conducted by telephone on May 11-13, 2012 among 615 adults nationwide, including 562 registered voters, who were first interviewed for a CBS News/New York Times Poll conducted April 13-17, 2012.

This might make for good narrative building, but it makes for a lousy scientific poll.

That's not to say that the poll is out of the ballpark. Rasmussen has Romney up four, Gallup has Obama up one. It is to say that any future polls by CBS News and the New York Times need to be taken with a lot of salt, until they fix their methodology.

The latest @CBSNews/@nytimes poll is suspect.

There's a massive selection bias in this poll:

Romney 46
Obama 43

Why do I say that there's a selection bias? Because:

This poll was conducted by telephone on May 11-13, 2012 among 615 adults nationwide, including 562 registered voters, who were first interviewed for a CBS News/New York Times Poll conducted April 13-17, 2012.

This might make for good narrative building, but it makes for a lousy scientific poll.

That's not to say that the poll is out of the ballpark. Rasmussen has Romney up four, Gallup has Obama up one. It is to say that any future polls by CBS News and the New York Times need to be taken with a lot of salt, until they fix their methodology.