Brackets!

How'd we do in projecting the final bracket? Not quite as well as previous years. This is disappointing because in past years, the tournament projections have been more accurate than the vast majority of the other prognosticators - especially from November through February. The bracket forecasts are based on Jay Coleman's OLD "Dance Card Formula". This formula was estimated quite a few years ago to model the behavior of the selection committee. Inevitably, the selection committe changes its behavior over time, so maybe this is not a huge surprise.

The good news is that Jay Coleman has just published a new version of his model. In fact, this new version predicted all but one of the at large bids - and the team missed (Florida versus Miss. St.) were ranked right next to each other and had very similar scores. For next season, we will use the improved updated formula and will also start projecting seeds instead of simply ranking them in order of probability of an at-large bid. Jay Coleman and his co-authors also have a new model that predicts seeds which will be used on this site.

Most pundits project brackets using a "what if the season ended today" framework. The approach taken on this site is to project what the field will look like on Selection Sunday. The advantage of combining the simulations on RPIforecast.com and the Dance Card formula is twofold: (1) The actual forecasts of RPI and records which feed into the formula are much more accurate than using the current RPI and record and (2) The Dance Card Formula (especially the new version) is objective and unbiased and does a remarkable job at predicting the field.