From prejudice to racial profiling and back: A naïve intuitive statistician’s curse

A designer conducts random searches to detect criminals, and may condition the search probability on individuals’ appearance. She updates her belief about the distribution of criminals across appearances using her search results, but incorrectly takes her sample distribution for the population distribution. In equilibrium she employs optimal search probabilities given her belief, and her belief is consistent with her findings. We show that she will be discriminating an appearance if and only if she overestimates the probability of this appearance’s being criminal. Notably, the ranking of two appearances’ being criminal may be reversed in equilibrium. Moreover, in a linear model, we provide conditions for uniqueness of the equilibrium and show how tightening the budget may worsen the situation of those most discriminated against. Finally, we demonstrate that our model can explain data from New York City, while a rational benchmark cannot. In particular, our results suggest that a policy change in 2013 has increased the aversion against being discriminating.

(joint with Manuel Förster)

Dominik Karos's homepage: http://www.imdokay.com