Criminal Behaviour and Immigration: An Application of some Estimators for Underreported Outcomes

This paper studies the individual level relationship between immigration and property crime in England and Wales using crime self-reports from the Crime and Justice Survey. Binary and count data models that account for under-reporting of criminal activity are used, since under-reporting is a major concern in self-reported crime data. The results indicate that under-reporting is considerably large, but, if anything, immigrants are less likely to under-report than natives. They also reveal that, once controlling for under-reporting and for basic demographic characteristics, even though not statistically significant, the effect of being an immigrant on crime is robustly negative across all model specifications (and statistically significant in some of those specifications). This might suggest that the negative association actually exists in the population, but the nature of the regression models in combination with the data in hand do not allow to estimate the relationship more precisely. We finally find that the effect of immigration status on property crime differs across regions and across ethnic groups.