Saturday, December 12, 2009
ESPN BracketBusters projections
As I have done in previous seasons, I've started making projections of what the records and RPIs for all 98 bracket buster teams will be on February 1, which is the day that they are set to announce the matchups. I've broken down by road and home teams. I'll probably update them once or twice a week - maybe more frequently. They can be found here: http://www.rpiforecast.com/bb.html
Subscribe to:
Post Comments (Atom)
2 comments:
hey man, this site is absolutely great!
i love sagarin, and ken pomeroy's numbers don't adjust for diminishing returns, but I can give you excel sheets that spit out game-probabilities based on ken pomeroy's stats if you'd like. I think Ken Pomeroy's predicted point margins actually run a little more accurately than Sagarin's--
you can either use the Log5 method (which pomeroy uses) or by the normal distribution (Point margin vs. standard deviation of Actual Minus Predicted Point Margin -- via Ken Pomeroy's predictive system)
either way, I'm very interested in your work!
Thanks. I love Ken's work, but if you look at the actual results in terms of predicting outcomes, Jeff Sagarin's are genenerally slightly more accurate in terms of mean squared error (at least in the past). Here's a site that keeps track of predictions versus outcomes:
http://www.thepredictiontracker.com/bbresults.php
Sagarin's Predictor has a mean squared error of about 145 at this point. It's one of the lowest. Ken Pomeroy's ratings are not included, but as I recall, the errors were slightly larger. This could have changed though.
I actually considered using Ken Pomeroy's ratings along side Sagarin's, and have though about including more, but
Post a Comment