On Feb 12, 2009, at 4:41 PM, Raph Frank wrote:
(Found something that might be it: http://saweis.net/svd/ )
Ah, that's the smart math way to do it with SVD.
Anyway, the basic point is that you can place each member of a legislature on a 2-d plane based solely on their voting records and then use that to predict future votes. You don't need to actually know what the votes are about.
Another play on it is what I did where I took the difference in voting record between any pair of senators to be a length and put all the pairings into a spring solver that tried to arrange the senators in a lowest energy configuration on a plane. That comes up with things like this:
http://bolson.org/gov/us/senate/2008/senate_current.svg
---- Election-Methods mailing list - see http://electorama.com/em for list info
