“I want to believe as much as the next person that particle physicists have discovered a Higgs boson, the so-called ‘God particle'”, writes author Stephen Ziliak in an op-ed appearing in a recent *Financial Post*. “But so far I do not buy the statistical claims being made about the discovery.”

Ziliak is talking about the last remaining theorized particle in quantum physics. It’s only now that scientists claim to have actually discovered one. The problem the ‘discovery’ raises with Ziliak, an economist, is not with the particle itself, but with the means used to find it—namely, the fact that the claim is based on *statistical significance.*

The Higgs boson has a mass of just “125 gigaelectronic volts”. Physicists searching for this imperceptible subatomic mass in the Large Hadron Collider are really searching for a tiny signal in the data that is unexpected enough to be “significant”. But significance does not imply certainty. The science has not actually proved the existence of the God particle, Ziliak contests; it has only proved that it is *more than likely*.

“They have fallen for a mistaken logic called in statistics the ‘fallacy of the transposed conditional,'” explains Ziliak. “If Mrs. Smith gets a cramp this week, and dies, one could not simply conclude that Mrs. Smith probably died from a cramp. This is because the probability of having a cramp, given that you are dead, is not equal to the probability that you are dead, given that you had a cramp. Mrs. Smith might have died for any number of other reasons.”

While statistical significance is a widely accepted measure across the sciences and other fields, Ziliak has been a vocal critic of its application. He has written an entire book on the subject, *The Cult of Statistical Significance*, along with co-author Dierdre N. McCloskey. You can read the full *Financial Post* article here.

Comments on this entry are closed.