Abstract
Ideally, the ranking of sports teams should incorporate information (comprehensiveness) obtained from the outcome of a match, such as the strength of the opponent and schedule. In addition, the ranking method should be fair and not reward teams for poor performance or factors beyond their control, such as the sequence of the matches. We state properties such that if followed, the ranking methods will be fair and comprehensive. We evaluate five popular sports ranking methods and whether or not they adhere to these properties. Further, we identify a ranking method that under reasonably sufficient conditions will satisfy all of the properties.
| Original language | English |
|---|---|
| Pages (from-to) | 776-787 |
| Journal | Journal of the Operational Research Society |
| Volume | 69 |
| Issue number | 5 |
| Early online date | 3 Jul 2017 |
| DOIs | |
| Publication status | Published - 4 May 2018 |
Keywords
- Markov chains
- ranking properties
- sports