The playoffs have begun! The seeding is as follows:
Eastern Conference: DCU, NE, CLB, NYRB, SKC
Western Conference: SEA, LA, RSL, FCD, VAN
MLS Cup Playoffs Projections can be found here.
Frequently Asked Questions
POFFpct refers to the chances of making the playoffs. CHG tracks the change in each team's playoff chances from last week (it has been reset for just this week). ShieldPct refers to the chances of finishing with the most points overall.
1) How does simulation work?
I calculate the probability of the possible outcomes (home win, tie, away win) in the remaining games based on each team's shot rates and finishing rates so far this season. Then, I let the simulator go through and pick which games are won and tied based on the those probabilities. If SKC has a 70% chance to beat NE at home, then the simulator will pick them 7 of 10 times, regardless of other simulated outcomes. All game outcomes are chosen in that manner, and at the end of each simulated season, the computer adds up all the teams' point totals and then ranks them within their respective conferences. By now, some teams have made the "computer playoffs," and some haven't. After 10,000 such simulations, we get a good idea of the proportion of times each team made the playoffs or won the Supporters' Shield.
Follow-up: Does your crush on Graham Zusi influence the model?
Good question. No.
2) Sooo...you only use data from this season to predict?
Yes and no. The estimates for how important the shot and finishing statistics are come from data going back to 2011. However, the predictors themselves are "within-season" predictors. Only 2012's first 16 games will be used to predict a team's 17th game, for example. Last season's influence on this season is noisy, I've learned.
3) Which data? Does this model use your fancy Expected Goals 2.0?
No. I haven't had time to crank that up yet! These predictions are calculated based on shot attempts, finishing rates, and strength of schedule.
4) How do you break ties?
The simulation counts the wins each team has accumulated during each simulated season, adding them to each team's current number of wins, which is the first tie-breaker by MLS rules. The simulation also calculates the goal differential expected based on a team's number of simulated wins, ties and losses, added to its present goal differential, which is the second tie-breaker used by MLS.