I'm beginning to get e-mails from folks who contend they can predict what the NCAA tournament selection committee with do come Sunday and also from those who say they have effective formulas for filling out tournament brackets.

Well, there will be no endorsements of bracket "systems" here, folks, but I'll pass along the ones that appear to have some merit or/and interest.

First, we'll deal with Selection Sunday. I have a news release from Mercer University, which has campuses throughout the state of Georgia. Mercer economics professor Allen Lynch and University of North Florida professor Jay Coleman have come up with models for predicting both the at-large teams for the tournament selection (the Dance Card) and for predicting brackets (the Score Card).

Over the course of several years, the Dance Card accuracy rate has been around 93 percent.

The latest predictions are based on games that only go up to March 11, so it's a little dated at the moment but here it is.

The Score Card model is pretty complicated, so I'll just quote from the news release:

"The Score Card formula suggests that only four pieces of information about each team are related to performance in the tournament: RPI (Ratings Percentage Index) value (i.e., the "old" RPI value); the ranking of the conference the team comes from (using the non-conference RPI ranking of each conference); whether the team won its regular season conference championship; and the number of wins in the last 10 games.

The Score Card formula predicted 79.68 percent of tournament games correctly in 2007 and 67.2 percent of games in 2006."

Here's some chart information on the Score Card.

As we get more of this stuff, we'll pass it along. If it does you any good, we expect a token of appreciation (just kidding). If it doesn't, hey, you got it for free, didn't you?