Methods
Monte Carlo Simulation
Estimating the chance of an outcome by playing it out many times with random draws and counting how often it happens.
How we use it
We simulate each game drive by drive 2,000 times: kickoffs, how far each drive gets, punts, field goals, turnovers, extra points and two-point tries, the clock and overtime. Counting results across those runs gives win probability and the predicted score.
The same simulator plays out each team's remaining schedule for projected wins, and plays every team against a league-average opponent for the power rankings.
Where to see it
Related terms
- Win Probability
- The model's estimated chance that a team wins a game, from the share of simulated games it wins. A 70% favorite should still lose about 3 games in 10.
- Projected Wins
- How many regular-season games a team is expected to finish with: its actual wins so far plus the wins from simulating the rest of its schedule.
- Simulated Win Rate
- The share of simulated games a team wins outright against a league-average opponent. It is the number our power rankings are sorted by.