Correlation is not Causation, not Even on Facebook

By Henry Woodbury

Caltech graduate student Virgil Griffith stirs the statistical pot:

Griffith used aggregated Facebook data about the favorite bands and books among students of various colleges and plotted them against the average SAT scores at those schools, creating a tongue-in-cheek statistical look at taste and intelligence….

Griffith came up with the idea as a way to show how to take two separate sets of data that were pretty straightforward on their own – in this case, the average SAT score and the favorite books among students at various universities – and combine them to become more interesting. Griffith says, “Their unity is hilarity incarnate. This is to inspire people to think creatively about the data sets that are on the Internet.”

Given Griffith’s puckish sense of humor, I read “think creatively” as “be skeptical.”

His other well-publicized “be skeptical” project is WikiScanner a tool that that uses IP addresses to identify anonymous Wikipedia edits made from corporate and government domains. (In my mind the joke here is the idea that Wikipedia is trustworthy in any fashion, but that’s just me.)