Saturday, March 15, 2008

Repeat After Me: Correlation Is Not Causation

Yesterday, the Star Tribune picked up a New York Times story about the recommendations of the National Mathematics Advisory Panel. It included this quote from the panel's report:

Students who complete Algebra II are more than twice as likely to graduate from college, compared to students with less mathematical preparation.
The panel's plan, then, is to guide all students toward Algebra II.

This reminds me of the book Freakonomics. Low-income kids who go to "better" schools have higher test scores, right? But when the kids were randomly assigned to schools in Chicago, the benefit went away -- the actual effect was from involved parents who pushed for the kids to go to the better schools. As the Freakonomics authors put it:
There are several ways in which two variables can be correlated. X can cause Y; Y can cause X; or it may be that some other factor is causing both X and Y (page 163).
I wonder if it occurred to the members of the math panel that their desired outcome (graduating from college) might actually be caused by some third factor that also causes completion of Algebra II... such as, perhaps, having parents who push them to take math. And that taking Algebra II by itself won't make kids more likely to graduate from college.

Just a thought from someone who never took Algebra II, but managed to graduate from college anyway.

No comments: