The chart above shows the correlation between chocolate consumption (per annum, per capita) and the number of Nobel Prize laureates per capita, by nation. It seems to show a very strong connection between the two. According to the author of the study, Franz Messerli of Columbia University,
“When you correlate the two – the chocolate consumption with the number of Nobel prize laureates per capita – there is an incredibly close relationship,” he says.
“This correlation has a ‘P value’ of 0.0001. This means there is a less than one-in-10,000 probability that this correlation is simply down to chance.”
But the author is trying to make a point about the use (and abuse) of statistics:
It might surprise you that we are trying to make a serious point. This is a classic case where correlation, however strong, does not mean causation.
Messerli gave us another example. In post-war Germany, the human birth rate fell along with the stork population. Were fewer storks bringing fewer babies?
The answer was that more homes were being built, destroying the storks’ habitat. And the homes were small – not the sort of places you could raise a large family in.
“This is a very, very common way of thinking,” he says.
“When you see a correlation, you do think there is causation in one way or another. And in general it’s absolutely true. But here we have a classic example where we cannot find a good reason why these two correlate so closely.”
Does Chocolate Make You Clever? [BBCNews]