Reply #63: OK, that's something

[OnTheOtherHand]

Yeah, obviously this isn't a game to you, accounting for these content-free responses. I actually care about the exit polls; I am still foolishly waiting for some indication that you do.

"1992? It was a good year."

Not for the exit polls, it wasn't. I hear over and over again about how accurate exit polls are, but when 1992 comes up, people mumble something and change the subject. althecat's version was, "The 1992 poll was nowhere near as large and as sophisticated as 2004s effort." Hmm. I always thought the talking point was supposed to be that the exit polls have a record of uncanny accuracy, not that we're pretty sure they became accurate sometime after 1992. (By the way, the 1992 national subsample has n = 15,490, so it's actually bigger than the 2004 national subsample.)

"New York? It is a northern state, in the US."

Where the exit polls projected Kerry winning by about 30 points, contradicting both official results and pre-election polls. So, did Kerry have a massive last-moment surge wiped out by widespread rigging of the lever machines? I don't think so, but if you do, won't you kindly make some effort to convince me that you take this exit poll result seriously?

"bush(co) doesn't do better where the red shift is bigger? Now that, that is a hard one. Because from where I sit, bushco does do better where the red shift is bigger. Isn't that what red shift means? That there is a noticeable shift from dem votes in 2000 to bushco in 2004 in same precincts."

No, that's not what it means. That is not remotely what it means. Red shift refers to the discrepancy between the exit polls and the official returns (or, rather, discrepancies in which Bush did better in the official returns). This isn't something I made up. Actually, I'm not sure who first came up with it -- maybe Jonathan Simon* -- but here is Alastair Thompson using it back in November 2004: http://www.scoop.co.nz/stories/HL0411/S00270.htm

This is the starting point of the exit poll controversy. How can you not know what it means?

*EDIT TO ADD: OK, I guess Febble is confident about that one. I think she paid a lot more attention to the exit polls back in 2004; I was mostly looking at Florida returns.