Wednesday, June 11, 2014

How to lie with statistics: the case of female hurricanes

I have flagrantly plagiarised the headline there from an excellent post by Paul Fritjers at Club Troppo; How to lie with statistics: the case of female hurricanes
I just came across an article in PNAS (the Proceedings of the National Academy of Sciences) with the catchy title ‘Female Hurricanes are deadlier than male hurricanes’. It is doing the rounds in the international media, with the explicit conclusion that our society suffers from gender bias because it does not sufficiently urge precautions when a hurricane gets a female name. Intrigued, and skeptic from the outset, I made the effort of looking up the article and take a closer look at the statistical analysis. I can safely say that the editor and the referees were asleep for this one as they let through a real shocker. The short of the story is that female hurricanes are no deadlier than male ones. Below, I pick the statistics of this paper apart.

He does indeed pick the statistics apart most notably because hurricanes in the USA have become less deadly over time and all hurricanes were given female names prior to 1978. When adjusted for this the results become insignificant. This study includes hurricanes back to 1950.

The authors rationalise that their flawed statistical difference is gender related because people think female names sound nicer so are more complacent for those hurricanes. Perhaps the death rate in the USA is itself a surprise compared to our own cyclonic experiences. (Note: Katrina was excluded as an outlier. No doubt if it had been named Hurricane Jim Bob all would have been saved.)

In Australia this story has been picked up by both News Ltd and the ABC.  I'm not aware that the Cairns Post has yet picked it up but I suspect Nick Dalton could really do something with this!

1 comment:

  1. The Guardian found you.