January 23, 2008

Value-added, with botulism

Before Kevin Carey proclaims that value-added [method] comes of age, he might want to read the real true facts behind the New York City teacher value-added project, wherein we learn that the city's great statistical experts thought three children were enough of a sample on which to base a teacher evaluation, or maybe the ethical problems with the NYC project, or maybe even my comments on value-added or growth measures in Accountability Frankenstein.

No matter what else you can say about growth measures, NYC's project is about the worst example I can imagine to use if one wanted to push the approach.

Update I: Carey responds in his post:

It might [have methodological problems, in NYC], I don't know, I guess we'll find out. But, per above, methodological issues can be worked out, and anyone who thinks the hysterical reaction to the value-added initiative stems from a deep and abiding concern for statistical integrity is willfully not paying attention.

The claim that "methodological issues can be worked out" is evidence that Carey hasn't read the writings of professional researchers who point out that growth models are no holy grail. I am one of those who have written about the difficulties inherent in growth models, but certainly not the only one.

And my response isn't hysterical; it's simply disgusted with the latest shenanigans from Tweed. The title comes from a wordplay (when food "comes of age," you don't really want it).

Update II: Best comment in response to Eduwonkette: skoolboy, who writes, "I'd characterize the New York City Department of Education as loving data but hating research."

Listen to this article
Posted in Accountability Frankenstein on January 23, 2008 10:54 AM |