‘Cult of Statistical Significance’ quoted on Slate; elsewhere, the authors continue the discussion

by Shaun Manning on October 5, 2012

In an article entitled “The Internet Blowhard’s Favorite Phrase” (also published as “Stop Saying That Correlation Does Not Imply Causation”), Slate writer Daniel Engber ponders how “a stats-class admonition become so misused and so widespread” as “the statistical cliché that closes threads and ends debates.”

“No, correlation does not imply causation, but it sure as hell provides a hint,” Engber said. Citing a recent study linking internet usage to depression–which, predictably, elicited the correlation/causation response online–Engber explained that that the lack of a definitive cause-effect relationship does not make the observation meaningless. “Does email make a man depressed? Does sadness make a man send email? Or is something else again to blame for both? A correlation can’t tell one from the other; in that sense it’s inadequate. Still, if it can frame the question, then our observation sets us down the path toward thinking through the workings of reality, so we might learn new ways to tweak them. It helps us go from seeing things to changing them.”

In the course of the discussion, Engber has cause to reference The Cult of Statistical Significance, Deidre McCloskey and Stephen Ziliak’s oft-praised and frequently debated book published by the University of Michigan Press in 2008. “To say that correlation does not imply causation makes an important point about the limits of statistics, but there are other limits, too, and ones that scientists ignore with far more frequency,” Engber wrote. He describes Cult as “an impassioned, book-length argument against the arbitrary cutoff that decides which experimental findings count and which ones don’t.”

“It’s easy to imagine how this point might be infused into the wisdom of the Web: ‘Facepalm. How many times do I have to remind you? Don’t confuse statistical and substantive significance!’ That comment-ready slogan would be just as much a conversation-stopper as correlation does not imply causation, yet people rarely say it,” Engber said.

The full eye-opening opinion piece can be read on Slate. Meanwhile, on Econ Journal Watch, Ziliak and McCloskey themselves offer a defense of their book’s themes in response to a recent comment by economist Thomas Mayer, continuing the debate.

Comments on this entry are closed.

Previous post:

Next post: