Model Predictions
| Model | Manhattan | Marist | Spread | Result |
|---|---|---|---|---|
| Elo | 58.0% | 42.0% | - | โ |
| Bradley-Terry | 63.0% | 37.0% | - | โ |
| Bradley-Terry Recency | 62.9% | 37.1% | - | โ |
| Margin | 57.3% | 42.7% | - | โ |
| Margin Recency | 57.6% | 42.4% | - | โ |
| Pythagorean | 59.9% | 40.1% | - | โ |
| Adjusted Efficiency | 74.6% | 25.4% | - | โ |
| Log Adjusted | 74.7% | 25.3% | - | โ |
| Points Off/Def | 56.2% | 43.8% | - | โ |
| Points Off/Def Recency | 56.5% | 43.5% | - | โ |
| Core Ensemble | 63.8% | 36.2% | - | โ |
| Recency Ensemble | 63.9% | 36.1% | - | โ |
| Dynamic Bradley-Terry | 62.6% | 37.4% | - | โ |
| Adjusted Context Blend | 63.2% | 36.8% | - | โ |
Actual: Marist -8 (73-81). Win probabilities: out-of-sample forecasts from the weekly fit before the game, the same forecasts as the model pages.