Abstract

Did German fl ying bombs really target the poorer areas of London—or did the poor people underneath them just think that they did? How many millions of dollars will the current re-make of King Kong really gross? Oh, and how many taxis are there in London? The human mind can make very good guesses, it seems—and it uses Bayesian analysis to do so. Tom Griffi ths and Joshua Tenenbaum explain. When people mention statistics and human cognition in the same sentence it is usually to complain about the limitations of the former when applied to the latter. For example, during World War II London was struck by German V-1 fl ying bombs and V-2 rockets. The locations at which they landed seemed to cluster in poorer parts of the city, and there was a widespread belief that these areas were being specifi cally targeted. After the war, the locations where the fl ying bombs fell were subjected to statistical analysis. It showed that they had fallen uniformly at random. The apparent clustering that people had perceived was just a coincidence. (For a discussion of this example, and of the general propensity for people to believe things that they should not, see Gilovich 1.) This reaction to the bombing of London is just one instance of a more general phenomenon of human thinking: a sense of coincidence that, all too often it seems, leads us to false conclusions. This tendency might suggest that statistics and human cognition are fundamentally not in accord. It is a view that gained prominent scientifi c support through the psychological research

Citations