We might be halfway through the first quarter of the first NFL playoff game of 2013, but I’m still finishing up with baseball and just getting warmed up on football. Football month on the blog officially kicks off today — there’s lots of interest stuff to come, from innovative rule ideas and play calling to new prediction methods and game analysis. Today, I’m trying an addition to the measure of NFL team quality that I debuted last year: True Wins. True Wins are calculated as follows:
True Win = Blowout Wins + Close Wins/2 + Close Losses/2 + Ties/2
You may recognize the intuition from pythagorean expectations — you get full credit for blowout wins (I define this as more than 7 points), but no extra credit for winning by huge margins, and you get half credit for all close games, since those probably come down to luck more than skill. Last year, I showed that True Wins predicts a little better than pythagoreans, and it’s a whole lot more direct. Both measures are much better than using wins alone, which unfairly penalize (reward) teams that lose (win) a lot of close games.
What Else is Luck-Driven? Fumble Recoveries?
With the playoffs coming right up, I decided to try an improvement that adjusts for possible luck in fumble recoveries as well. Here’s the logic (from Football Outsiders):
Stripping the ball is a skill. Holding onto the ball is a skill. Pouncing on the ball as it is bouncing all over the place is not a skill. There is no correlation whatsoever between the percentage of fumbles recovered by a team in one year and the percentage they recover in the next year. The odds of recovery are based solely on the type of play involved, not the teams or any of their players . . . Fumble recovery is a major reason why the general public overestimates or underestimates certain teams. Fumbles are huge, turning-point plays that dramatically impact wins and losses in the past, while fumble recovery percentage says absolutely nothing about a team’s chances of winning games in the future. With this in mind, Football Outsiders stats treat all fumbles as equal, penalizing them based on the likelihood of each type of fumble (run, pass, sack, etc.) being recovered by the defense.
The keys are:
- Fumbles are huge turning points in games
- Teams don’t maintain high or low recovery rates over time
To quantify #1, I determined the point value of a recovery. A simple regression of point differential in each game on total fumbles and fumbles recovered shows that, holding the number of total fumbles constant for each team, a home team fumble is worth about 2.8 points of point differential, and an away team fumble is worth about 3.7 points of point differential in the other direction.* Imagine a game where each team fumbles four times, but the home team recovers none while the visitors recover all four. Adjusting both teams to the average recovery rate of 2.2 out of four fumbles (about 56%, which includes fumbles nullified by penalties and replay reviews) changes the point differential by over ten points.
True Wins Plus: Fumble Adjusted
The last part is easy: True Wins Plus adjusts point differentials by these values to reflect the average recovery rate instead of the actual recovery rate in the game. The resulting scorelines should be more indicative of team quality, so I use them as the inputs in the True Wins formula above. Here are the prediction results for playoff games, taking the team with the higher number of wins, True Wins, and True Wins Plus in each match up (no prediction when they tie):
Interestingly, True Wins Plus lies somewhere between True Wins and actual wins for prediction in this limited sense. I’ll have some more analysis coming soon testing the randomness of fumbles, including better fumble data hopefully. For the meantime, here are the True Win standings for the playoff teams this year to keep you busy:
It’s a curious year — the AFC is extremely top heavy and the NFC is incredibly balanced. The Indianapolis Colts are the Big Pretenders of 2012, taking the mantle from the Broncos last year (a 6.5 True Win playoff team!). The Colts have a full four win deficit between True Wins and actual wins; only that other Colts quarterback has been able to maintain a “Luck” streak like that over the long haul.
Today’s predictions: Houston beats Cincinnati but it’s very close, and Green Bay takes care of Minnesota. Tomorrow, Baltimore should roll the Big Pretenders, and as much as I like Seattle’s 11 True Wins and strong recent performance, it’s hard to ignore their 3-5 road record. It should be a close game with Washington.
Football month is on it’s way . . .
* Collecting data on total fumbles was surprisingly hard. I ended up scraping play by play data off the web, then processing each play to hunt for fumbles. Even after that, some fumbles may be assigned to the wrong team due to errors and idiosyncracies in the play by play data. I may be able to get better play by play data directly from the league now, and I also think I could scrape the fumble information directly. Also, it’s important to control for total fumbles in these regressions, since, as stated by the FO guys, fumbling is related to skill. Only after fixing the number of fumbles can I consider the number of lost fumbles to be somewhat random.