Posted by Chase Stuart on October 17, 2010
Regular PFR readers will recall that we published college football SRS ratings every week last season. With seven weeks in the books, and the BCS opening rankings coming out tonight, it made sense to start up the project for 2010. So how do we come up with SRS grades for college football teams?
PFR has used the Simple Rating System to grade college and NFL teams for years. All ratings or rankings are meaningless without explanation, and the link above explains what the SRS tries to do. The SRS version that I'm implementing below is most useful to predict future results; the SRS is predictive, not retrodictive. That means the SRS will have no trouble at all ranking a team that's undefeated and beat a team with one loss behind the very team it beat. Why? One, because we know that one game is just one game, and never is conclusive proof that one team is better than another; and two, because the SRS weighs each game equally. Of course, sample size issues are always present here; while I've waited for seven weeks before presenting the SRS, we really need to see a couple more weeks of action before we can have full faith in this system. For now, though, maybe they'll make you rethink your perception of a couple of teams.
So how am I calculating these simple ratings?
1) For each game, 3 points are given to the road team (unless it's a neutral site game). After that adjustment, all wins and losses of between 7 and 24 points are scored as however many points the team won by. So a 24-10 road win goes down as +17 for the road team, -17 for the home team.
2) Wins of 7 or fewer points are scored as 7-point wins and losses of 7 or fewer points are scored as 7 point losses, except that road losses of 3 or fewer and home wins of 3 or fewer are graded as 0 point ties. So a 21-20 home victory goes down as a tie for both teams. This is not as drastic as it sounds, because the SRS ultimately is not concerned with win/loss records. There is no distinction between a win and a loss (you don't need to make such distinctions in predictive systems) except for when the game is close. So three 10-point wins scores +30, just as two 20-point wins and a 10-point loss scores as +30. However, three 3 point wins (+9 before the adjustments, +21 after) is worth more than two 10 point wins and a 1 point home loss (+21 before, +13 after).
3) Wins/Losses of more than 24 points are scored as the average between the actual number and 24. This is to avoid giving undue credit to teams that run up the score. Oregon bludgeoned New Mexico on opening day, 72-0, but that "only" goes down as a 46.5 point win. Why? Because the game was in Eugene (dropping it to +69) and the average of 24 and 69 is 46.5. However, in FCS/I-AA games, there is no run-up-the-score modifier. Why? Otherwise, the elite teams could beat the FCS cupcakes by 64 points and go down in this system. Major thanks to Peter R. Wolfe for providing the game scores.
Doug (and the readers) might argue that I've taken the first "S" out of the SRS, but I think these ratings are still simple. They're merely designed to get an approximate rating on how strong each team really is. By using just points scored and points allowed, we're obviously leaving lots of information behind. That's why I still think these are pretty simple, but a large improvement over looking at just points differential or won/loss records.
After translating the raw scoring differential using the system above to a "SRS" victory margin, I simply add the victory margin for each game to the strength of schedule for the opponent. A 24-point win over an average team is equivalent to a 14-point win over a team that's 10 points better than average. I ran hundreds of iterations to figure out the true strength of schedule for each opponent and the true rating for each team; this involves adjusting the SOS of each team's opponents by the SOS of those opponents, and so on. Don't worry: at the end, the results converge, and we have true and legitimate ratings. My favorite part about the SRS is that everything adds up at the end. So after posting the ratings for each team, you could go through the schedule of any of the 120 FBS teams and understand exactly why their rating was what it was. I'll do that below with the top five teams. First, the results:
|35||North Carolina St||7||11.3||39.4||50.7||5-2||ACC||5||57|
|38||San Diego St||6||15.8||34.1||49.8||4-2||MWC||4||92|
|101||San José St||7||-19.8||47.8||28.0||1-6||WAC||8||9|
|112||Middle Tennessee St||6||-4.4||26.1||21.7||2-4||SunB||6||119|
|118||New Mexico St||6||-22.6||36.3||13.7||1-5||WAC||9||82|
So how do Oregon, Stanford, TCU, Boise State and -- Missouri come out on top?
Oregon put their foot on the throats of Portland State, New Mexico and Tennessee, and outlasted Stanford and Arizona. Their 20 point win against Washington State (which fell far short of covering the spread) was their worst performance of the season so far.
Stanford gets penalized for losing to Oregon, but that was their worst game of the year. Blowout wins over respectable UCLA and Notre Dame teams were impressive, and Stanford has looked good for 5.5 games so far.
|4-Sep-10||TCU||30||Oregon St||21||Arlington TX||9||54.1||63.1|
No one has been as consistent as TCU: Their worst game of the year was a 27-0 win in Fort Collins. They beat Oregon State, the best team they faced, and blew out Baylor, the only other legitimate team they've faced so far. But TCU is most impressive for their consistent dominance. They've allowed just three points in three games in October.
|16-Oct-10||Boise St||48||San José St||0||Road||37.5||28.0||65.5|
|25-Sep-10||Boise St||37||Oregon St||24||Home||10||54.1||64.1|
|2-Oct-10||Boise St||59||New Mexico St||0||Road||43||13.7||56.7|
|6-Sep-10||Boise St||33||Virginia Tech||30||Landover MD||3||53.5||56.5|
That huge victory over Virginia Tech on opening night? That's the least impressive game for the Broncos this year, according to the SRS. Boise State has won by 40+ in four other games, and handled Oregon State much easier than the 13-point margin would have you think.
|4-Sep-10||Missouri||23||Illinois||13||St Louis MO||10||50.5||60.5|
|18-Sep-10||Missouri||27||San Diego St||24||Home||0||49.8||49.8|
Missouri's two best games came the last two weeks. They've played an easy schedule, but dominated the Aggies in College Station this past Saturday. The win over Illinois looks better now that the Illini won in State College and were competitive against the Buckeyes. Missouri surprisingly comes in fifth in this modified margin of victory category, thanks to ranking second in college football in points allowed. The Tigers haven't had a difficult schedule, but it hasn't been full of cupcakes, either. I wouldn't book my Fiesta Bowl tickets just yet if I was Jason -- squeaking by San Diego State isn't a very good sign but Missouri seems to be underrated so far by the national media. The Sooners come to Columbia this weekend (as does Gameday), so we'll get an answer on how good Missouri is very soon.