top of page

With the current SEC Game of the Year in our window, Auburn strengthens its grip at the top. Of course a close road loss will not hurt Tennessee all that much at all. On the other hand, UConn's loss at Xavier puts them as MY last team in. I am sure they are safer in real life, but you gotta actually win some games at some point.


The Method

Basically this is the same as what I am doing for football. The components.

  1. Bradley-Terry model using a small margin of victory component. This is more or less a logistic regression. A team gets 1 point for having a better rating than a competitor.

  2. Head to Head record. A team gets as many points as net wins over a competitor. (no negative points for a team with a losing record)

  3. Record vs Common Opponents. A pairwin here is worth 1 point.

  4. Regular season leader. During the season we will use the highest rated team with the fewest conference losses (then the team with most pairwins based on criteria 1-3 as a tiebreaker). A pairwin here is worth 0.5 points. Based on how the committee seeded teams last year, 0.5 points fit the data better than 0 or 1.


For each component, a team is compared to the other 365 teams (all non D1 are treated as a single opponent) and points are awarded. Whichever head to head has more points counts a pairwin.


For example: Team A has a better rating than Team B, but they had no head to head, Team B did better against common opponents, and Team A was the regular season champ of its conference. In this example Team A has 1.5 points (1 for rating, 0.5 for reg season champ). Team B has 1 point for common record. Team A would get the overall pairwin.


Half pairwins are used for ties. The team with the most pairwins is the #1 overall team. If there is a tie in pairwins, the Bradley-Terry rating is used as a tiebreaker.


The Field of 68

Through the games of 01/26/2025. Now with some good teams playing each other, at least the field is looking like a plausible tournament field. The SoS is based on the perspective of a .500 team (using the Bradley-Terry rankings as weights)



The Bubble

The first 4 teams are in the field with byes to the Round of 64. Teams 5-8 are the play-in teams. The others are out in order. As you can see, the model is pretty dumb right now, but it is fun to watch it get smarter.






 
 
 

The SEC continues to dominate the field and the season. That said, Duke continues its absolute rampage through the ACC. The Feb 22 game against Illinois is suddenly looming very large. Meanwhile, St Mary's is doing what St Mary's does - and with Gonzaga going down at Oregon State, they are at the top of the West Coast conference.


The Method

Basically this is the same as what I am doing for football. The components.

  1. Bradley-Terry model using a small margin of victory component. This is more or less a logistic regression. A team gets 1 point for having a better rating than a competitor.

  2. Head to Head record. A team gets as many points as net wins over a competitor. (no negative points for a team with a losing record)

  3. Record vs Common Opponents. A pairwin here is worth 1 point.

  4. Regular season leader. During the season we will use the highest rated team with the fewest conference losses (then the team with most pairwins based on criteria 1-3 as a tiebreaker). A pairwin here is worth 0.5 points. Based on how the committee seeded teams last year, 0.5 points fit the data better than 0 or 1.


For each component, a team is compared to the other 365 teams (all non D1 are treated as a single opponent) and points are awarded. Whichever head to head has more points counts a pairwin.


For example: Team A has a better rating than Team B, but they had no head to head, Team B did better against common opponents, and Team A was the regular season champ of its conference. In this example Team A has 1.5 points (1 for rating, 0.5 for reg season champ). Team B has 1 point for common record. Team A would get the overall pairwin.


Half pairwins are used for ties. The team with the most pairwins is the #1 overall team. If there is a tie in pairwins, the Bradley-Terry rating is used as a tiebreaker.


The Field of 68

Through the games of 01/16/2025. Now with some good teams playing each other, at least the field is looking like a plausible tournament field. The SoS is based on the perspective of a .500 team (using the Bradley-Terry rankings as weights)



The Bubble

The first 4 teams are in the field with byes to the Round of 64. Teams 5-8 are the play-in teams. The others are out in order. As you can see, the model is pretty dumb right now, but it is fun to watch it get smarter.






 
 
 

In real life, I am not sure UConn's ranking is actually in peril - but they do need to start beating more teams to feel good. This might end up being the committee and this one man committee's biggest disagreement.


The Method

Basically this is the same as what I am doing for football. The components.

  1. Bradley-Terry model using a small margin of victory component. This is more or less a logistic regression. A team gets 1 point for having a better rating than a competitor.

  2. Head to Head record. A team gets as many points as net wins over a competitor. (no negative points for a team with a losing record)

  3. Record vs Common Opponents. A pairwin here is worth 1 point.

  4. Regular season leader. During the season we will use the highest rated team with the fewest conference losses (then the team with most pairwins based on criteria 1-3 as a tiebreaker). A pairwin here is worth 0.5 points. Based on how the committee seeded teams last year, 0.5 points fit the data better than 0 or 1.


For each component, a team is compared to the other 365 teams (all non D1 are treated as a single opponent) and points are awarded. Whichever head to head has more points counts a pairwin.


For example: Team A has a better rating than Team B, but they had no head to head, Team B did better against common opponents, and Team A was the regular season champ of its conference. In this example Team A has 1.5 points (1 for rating, 0.5 for reg season champ). Team B has 1 point for common record. Team A would get the overall pairwin.


Half pairwins are used for ties. The team with the most pairwins is the #1 overall team. If there is a tie in pairwins, the Bradley-Terry rating is used as a tiebreaker.


The Field of 68

Through the games of 01/09/2025. Now with some good teams playing each other, at least the field is looking like a plausible tournament field. The SoS is based on the perspective of a .500 team (using the Bradley-Terry rankings as weights)



The Bubble

The first 4 teams are in the field with byes to the Round of 64. Teams 5-8 are the play-in teams. The others are out in order. As you can see, the model is pretty dumb right now, but it is fun to watch it get smarter.






 
 
 

© 2035 by Annabelle. Wix

LET'S TAKE IT TO THE NEXT LEVEL

Thanks for submitting!

bottom of page