Model Predictions
| Model | Marist | Manhattan | Spread | Result |
|---|---|---|---|---|
| Elo | 39.5% | 60.5% | - | โ |
| Bradley-Terry | 50.6% | 49.4% | - | โ |
| Bradley-Terry Recency | 50.7% | 49.3% | - | โ |
| Margin | 38.3% | 61.7% | - | โ |
| Margin Recency | 38.6% | 61.4% | - | โ |
| Pythagorean | 45.2% | 54.8% | - | โ |
| Adjusted Efficiency | 54.6% | 45.4% | - | โ |
| Log Adjusted | 54.9% | 45.1% | - | โ |
| Points Off/Def | 27.7% | 72.3% | - | โ |
| Points Off/Def Recency | 27.8% | 72.2% | - | โ |
| Core Ensemble | 42.1% | 57.9% | - | โ |
| Recency Ensemble | 42.1% | 57.9% | - | โ |
| Dynamic Bradley-Terry | 31.3% | 68.7% | - | โ |
| Adjusted Context Blend | 14.2% | 85.8% | - | โ |
Actual: Manhattan -4 (60-64). Win probabilities: out-of-sample forecasts from the weekly fit before the game, the same forecasts as the model pages.