March 2018
Beginner
256 pages
3h 56m
English
“Petabytes allow us to say: ‘Correlation is enough.’”
—Chris Anderson,Wired, June 23, 2008
The sentiment expressed by Chris Anderson in 2008 is a popular meme in the big data community. “Causality is dead,” say the priests of analytics and machine learning. They argue that given enough statistical evidence, it’s no longer necessary to understand why things happen—we need only know what things happen together.
But inquiring whether correlation is enough is asking the wrong question. For consumers of big data, the key question is, “Can I take action on the basis of a correlation finding?” The answer to that question is, “It depends”—primarily on two factors: