The Policy Debate Central team is excited to launch a new ranking system based on the Elo rating system best known for its use in professional Chess. While the Elo system is certainly not new to the world of policy debate, it has fallen out of use even though it is very present in other forms of debate.

Before we present the first rankings, a brief introduction to Elo rating systems. The Elo rating system is a rating algorithm that uses relative strengths of teams to create rankings. This is designed to correct for inaccuracies in win percentage as a measurement of team ranking and reduce the random variability from pairings.

In particular, this model uses a $K$-factor of 16 due to the reasonably small sample size and simulates a debate season 100 times in order to minimize variance that results from chronology and individual tournament results. Only TOC bid tournaments are included, with each being weighted equally.

The accuracy of this model in predicting the winner of debates is 89.275%. No system can perfectly forecast results. That said, our model offers a reliable benchmark for assessing a team’s standing relative to others throughout the season, even though it’s not a definitive measure of success.

These rankings include data from every tournament up to the weekend of the Greenhill Fall Classic and the Washburn Rural Debate Invitational. Only the top 100 Elo ratings are shown.

If you have any suggestions for what you’d like to see these rankings reflect, let us know here. There are a few duplicate team errors we will fix in the next ranking!