Because of the holidays, I’m very likely to skip week 16 of this series. On week 17, after all the games are played, we’ll make playoff predictions based on the data we’ve calculated.

~~~

To explain the columns below, Median is a median point spread, and can be used to get a feel for how good a team is without overly weighting a blowout win or blowout loss. HS is Brian Burke’s Homemade Sagarin, as implemented in Maggie Xiong’s PDL::Stats. Pred is the predicted Pythagorean expectation. The exponent for this measure is fitted to the data set itself. SOS, SRS, and MOV are the simple ranking components. MOV is margin of victory, or point spread divided by games played. SOS is strength of schedule. SRS is the simple ranking.

Some notes: there appear to be 6, perhaps 7 elite teams, ones with real chances to go deep into the playoffs. That said, the history  of the past 10 Super Bowls is that a dark horse has made it to the finals 4 of the last 10 times (New England in 2001, Carolina in 2003, New York Giants in 2007, Arizona in 2008) and further, the dark horse has either won or made the game quite interesting. In the playoffs, while home field advantage counts, regular season records, or offensive stats of any kind, are not statistically predictive.

If one were to create a “dangerous team” stat, subtracting the current record of a team (as a percentage) from their Pythagorean, then the most dangerous team presently must be the Miami Dolphins, with the Eagles close behind. Such a measure though, applied to the Denver Broncos, doesn’t adequately capture the Broncos winning streak, nor the  fascination with this team. I’ve long wondered how well scoring analysis captures the kinds of teams that win by a little and lose by a lot. Another team  in that category would be Kansas City, capable of some impressive wins, but also embarrassing losses.

If you need a case study in a statistically anomalous team that won, an interesting one would be the 1976 Oakland Raiders.