Model Predictions
| Model | George Mason | William & Mary | Spread | Result |
|---|---|---|---|---|
| Elo | 69.8% | 30.2% | - | โ |
| Bradley-Terry | 72.6% | 27.4% | - | โ |
| Bradley-Terry Recency | 72.5% | 27.5% | - | โ |
| Margin | 59.6% | 40.4% | - | โ |
| Margin Recency | 60.0% | 40.0% | - | โ |
| Pythagorean | 70.0% | 30.0% | - | โ |
| Adjusted Efficiency | 79.5% | 20.5% | - | โ |
| Log Adjusted | 79.6% | 20.4% | - | โ |
| Points Off/Def | 52.6% | 47.4% | - | โ |
| Points Off/Def Recency | 53.1% | 46.9% | - | โ |
| Core Ensemble | 65.9% | 34.1% | - | โ |
| Recency Ensemble | 65.9% | 34.1% | - | โ |
| Dynamic Bradley-Terry | 63.4% | 36.6% | - | โ |
| Adjusted Context Blend | 78.5% | 21.5% | - | โ |
Actual: William & Mary +3 (85-82). Win probabilities: out-of-sample forecasts from the weekly fit before the game, the same forecasts as the model pages.