From Michael Winerip's NYT article:
The calculation for Ms. Isaacson’s 3.69 predicted score is even more daunting. It is based on 32 variables — including whether a student was “retained in grade before pretest year” and whether a student is “new to city in pretest or post-test year.”
Those 32 variables are plugged into a statistical model that looks like one of those equations that in “Good Will Hunting” only Matt Damon was capable of solving.
I'll have more to say about this later. I don't think Winerip really understands what's going on here but the story's definitely worth a read.
Update: it is now later.