Model Predictions
| Model | Brown | Harvard | Spread | Result |
|---|---|---|---|---|
| Elo | 70.5% | 29.5% | - | โ |
| Bradley-Terry | 59.9% | 40.1% | - | โ |
| Bradley-Terry Recency | 66.0% | 34.0% | - | โ |
| Margin | 45.9% | 54.1% | - | โ |
| Margin Recency | 49.1% | 50.9% | - | โ |
| Pythagorean | 54.7% | 45.3% | - | โ |
| Adjusted Efficiency | 58.7% | 41.3% | - | โ |
| Log Adjusted | 58.7% | 41.3% | - | โ |
| Points Off/Def | 45.1% | 54.9% | - | โ |
| Points Off/Def Recency | 48.4% | 51.6% | - | โ |
| Core Ensemble | 60.6% | 39.4% | - | โ |
| Recency Ensemble | 61.3% | 38.7% | - | โ |
| Dynamic Bradley-Terry | 75.9% | 24.1% | - | โ |
| Adjusted Context Blend | 46.8% | 53.2% | - | โ |
Actual: Harvard -13 (80-93). Win probabilities: out-of-sample forecasts from the weekly fit before the game, the same forecasts as the model pages.