Model Predictions
| Model | Saint Peter's | Canisius | Spread | Result |
|---|---|---|---|---|
| Elo | 18.6% | 81.4% | - | โ |
| Bradley-Terry | 37.9% | 62.1% | - | โ |
| Bradley-Terry Recency | 36.0% | 64.0% | - | โ |
| Margin | 30.4% | 69.6% | - | โ |
| Margin Recency | 29.3% | 70.7% | - | โ |
| Pythagorean | 43.6% | 56.4% | - | โ |
| Adjusted Efficiency | 26.7% | 73.3% | - | โ |
| Log Adjusted | 26.6% | 73.4% | - | โ |
| Points Off/Def | 30.4% | 69.6% | - | โ |
| Points Off/Def Recency | 29.2% | 70.8% | - | โ |
| Core Ensemble | 30.1% | 69.9% | - | โ |
| Recency Ensemble | 29.9% | 70.1% | - | โ |
| Dynamic Bradley-Terry | 32.1% | 67.9% | - | โ |
| Adjusted Context Blend | 16.1% | 83.9% | - | โ |
Actual: Canisius +7 (84-77). Win probabilities: out-of-sample forecasts from the weekly fit before the game, the same forecasts as the model pages.