Does unemployment increase crime? Evidence from US data 1974-2000

OLS may understate the effect of unemployment on crime because of the endogeneity problem (Raphael and Winter-Ember 2001). In this paper we use changes in the real exchange rate, state manufacturing sector percentages, and state union membership rates as novel instrumental variables to carry out 2SLS estimations. We find a one-percentage-point increase in unemployment would increase property crime by 1.8 percent under the OLS method, but that the elasticity goes up to 4 percent under 2SLS. The larger 2SLS effect has significant policy implications because it explains 30 percent of the property crime change during the 1990s.