You readers know I’m a huge fan of Chris Brown’s Smart Football blog. And you also know that “regression to the mean” is one of my big mantras for Georgia’s prospects this season. So if Chris posts something on that subject, I’m gonna pay attention.
Linking to a WSJ piece, he references the following with regard to non-BCS bowl teams,
… The reason is a statistical principle called regression to the mean that is critical in sports, yet poorly understood. A player’s or team’s actual performance is an imperfect indicator of underlying ability. Luck — or statistical noise, if you prefer — also plays a role. Generally those who do well are better than average, but they’ve also probably had more luck than average. And the opposite is true of players or teams that do badly. SI . . . isn’t accounting for the underlying forces that are pushing these above-average teams — losing teams need not apply — back to average. After all, some of the teams that missed the bowl games this year are going to qualify next year…
and then adds this qualifier
I agree with this, but would only add that path dependence is likely a strong mitigant of mean regression when it comes to the biggest BCS teams, due to recruiting advantages and so on.
My first thought on reading that is well, dayum. I don’t want to hear about strong mitigants after a season when Georgia finished minus-16 in turnover margin. Then I clicked on his link to the definition of “path dependence” and got this:
Path dependence explains how the set of decisions one faces for any given circumstance is limited by the decisions one has made in the past, even though past circumstances may no longer be relevant.
The phrase is regularly used to mean one of two things (Pierson 2004):
- Some authors use path dependence to mean simply “history matters” – a broad concept;
- Others use it to mean that institutions are self reinforcing – a narrow concept.
It is the narrow concept that has the most explanatory force and of which the discussions below are examples. The claim “history matters” is trivially true and reduces simply to “everything has causes”.
If I understand that correctly, Mark Richt’s decision to replace three members of his defensive staff ought to serve as a mitigant to the mitigant. Particularly so, given the macro changes to the entire scheme, but also on the micro level in terms of changes in technique, like this:
… Rambo spoke excitedly about his off-season work and Georgia’s new defensive backs coach, Scott Lakatos.
“I take notes on everything he says, know[ing] it’ll help me out in the long run,” Rambo said. “It’s a whole lot different, especially with the footwork Coach Lakatos is teaching us. Most of the people in the NFL run the same thing Coach Lakatos is teaching us. . . . I’ll imagine myself making more plays this year.”
Am I reading too much into all of this and feeling more optimism than is justified? What do you guys think?