Abstract

This study examines whether the number of citizens fatally shot by police in the United States has changed significantly since the shooting of Michael Brown in Ferguson, Missouri. Using longitudinal data compiled by killedbypolice.net, we use an interrupted time-series design to test the effect of events in Ferguson on fatal shootings by police. Our analyses reveal that the number of citizens killed by police is temporally unstable, exhibiting random short-term fluctuations that are often misinterpreted as evidence of substantively meaningful trends. However, after testing a variety of model specifications, we find no evidence that the number of fatal police shootings either increased or decreased post-Ferguson. Claims to the contrary are based on weak analyses of short-term trends.