Model Predictions
| Model | Harvard | Vermont | Spread | Result |
|---|---|---|---|---|
| Elo | 32.4% | 67.6% | - | โ |
| Bradley-Terry | 43.9% | 56.1% | - | โ |
| Bradley-Terry Recency | 42.8% | 57.2% | - | โ |
| Margin | 36.9% | 63.1% | - | โ |
| Margin Recency | 35.6% | 64.4% | - | โ |
| Pythagorean | 66.4% | 33.6% | - | โ |
| Adjusted Efficiency | 53.8% | 46.2% | - | โ |
| Log Adjusted | 53.7% | 46.3% | - | โ |
| Points Off/Def | 34.5% | 65.5% | - | โ |
| Points Off/Def Recency | 33.1% | 66.9% | - | โ |
| Core Ensemble | 41.2% | 58.8% | - | โ |
| Recency Ensemble | 40.9% | 59.1% | - | โ |
| Dynamic Bradley-Terry | 38.7% | 61.3% | - | โ |
| Adjusted Context Blend | 20.4% | 79.6% | - | โ |
Actual: Vermont +7 (78-71). Win probabilities: out-of-sample forecasts from the weekly fit before the game, the same forecasts as the model pages.