My 2010 NCAA Tournament Rating Methods
- 2 Comment
On March 21st I presented some work on rating college basketball teams with an emphasis on estimating win probabilities in future games at SIAM-SEAS 2010. You can download the following presentation for more details of the methods:
Estimating the Probability of Winning a College Basketball Game
In this presentation I look at two ways of modeling college basketball team efficiency data: net efficiency per game (linear regression) and the number of points a team scores on a possession (multinomial logistic regression).
These models allow you to estimate various probabilities of events, and the table below lists estimates for each team’s chances of winning the 2010 NCAA tournament:
| Team | Linear | Multinomial |
|---|---|---|
| Duke | 58.9% | 51.7% |
| West Virginia | 18.1% | 19.9% |
| Michigan St | 14.0% | 16.9% |
| Butler | 8.9% | 11.5% |
Both of these models estimate that Duke has a better chance of winning the tournament than the experts estimate, so take these estimates for what they’re worth: imperfect estimates of reality that agree that Duke should be the favorite to win the tournament.
The presentation goes better with an explanation, so post in the comments if you’ve got any questions about what I’m doing with the data.
If you enjoyed this post, use RSS to get notified of new posts.
2 Comments on this post
Trackbacks
-
David Hess said:
Nice presentation, this is something I’ve wanted to try for a while, but don’t have much experience with multinomial regression, so I’ve been putting it off.
One question: are the values used in the regressions adjusted for schedule strength? It would be fairly easy to do so in the linear model, given Pomeroy’s data. But adjusting estimates for points on individual possessions seems difficult. I’ve got some ideas floating around in the back of my head, but don’t have the data set to try them out.
April 1st, 2010 at 3:23 pm -
Ryan said:
David, the model estimates offensive and defensive ratings for each team for each point total. The fit of the model is what adjusts these offensive and defensive ratings for opponent strength!
April 8th, 2010 at 2:23 pm