Selfies and sharks, and statistical dangers

Comparisons of selfies and sharks, and of pretty much any pair of things, come out differently depending on how careful you are in making — or judging — the comparison. Gary Smith, of Ponona College, explains:

We are now told that selfies are more than dangerous than sharks, with 8 deaths this year from shark attacks this year, compared to 12 reported deaths related to taking ill-advised selfies. It is a funny story, but it is a classic mistake.

The selfie/shark story reminds me of a book that once calculated the probabilities of “being injured by various items around your house” and concluded that, “As the figures show, our homes are veritable booby traps. Even your cocktail table is out to get you. These accounted for almost 64,000 injuries, more than all ladders [62,000 injuries].” With 74,050,000 U.S. households, they calculated the probability of being injured by a cocktail table as 64,000/74,050,000 = 0.00086 and the probability of being injured by a ladder as 62,000/74,050,000 = 0.00084.

These calculations are the probability that a reported injury involved a table or ladder, not the probability of being injured by using a table or ladder. A study of the dangers of tables and ladders should take into account how often tables and ladders are encountered, not how many households there are.

In the same way, to calculate the probability of being injured while taking a selfie, we need to divided 12 by the number of selfies taken (a lot!), and compare this to 8 divided by the number of swims in shark-infested waters (not so many!).

If we apply the selfie/shark mistake to other Darwinian activities, we might conclude that selfies are more dangerous than swallowing knifes and juggling chain saws. Don’t.