Our team develops cutting-edge statistical techniques to measure racial bias in policing, evaluate policing policy reforms, and improve the performance of policing organizations.
Diversity in Policing: The Role of Officer Race and Gender in Police-Civilian Interactions in Chicago
Using newly collected personnel data and millions of ultra-fine-grained records on officer deployment and behavior, we conduct a detailed quantitative case study of diversity in the Chicago Police Department. We show how officers from marginalized groups are consistently assigned to different working conditions than white and male officers, meaning they typically encounter vastly different circumstances and civilian behaviors. Compared with white officers facing identical conditions, we show Black and Hispanic officers both make substantially fewer stops, arrests, and use force less often, especially against Black civilians. Much of the gaps in stops and arrests are due to a decreased focus on discretionary contact, such as stops for vaguely defined “suspicious behavior.” Within all racial/ethnic groups, female officers are substantially less likely to use force relative to male officers.
We show that if police racially discriminate when choosing whom to investigate, analyses using administrative records to estimate racial discrimination in police behavior are statistically biased, and many quantities of interest are unidentified – even among investigated individuals – absent strong and untestable assumptions. Using principal stratification in a causal mediation framework, we derive the exact form of the statistical bias that results from traditional estimation. We develop a bias-correction procedure and nonparametric sharp bounds for race effects, replicate published findings, and show the traditional estimator can severely underestimate levels of racially based policing or mask discrimination entirely. We conclude by outlining a general and feasible design for future studies that is robust to this inferential snare.
Using a rare geocoded census of SWAT team deployments from Maryland, we show that militarized police units are more often deployed in communities with large shares of African American residents, even after controlling for local crime rates. Using nationwide panel data on local police militarization, we demonstrate that militarized policing fails to enhance officer safety or reduce local crime. Finally, using survey experiments – one of which includes a large oversample of African American respondents – we show that seeing militarized police in news reports may diminish police reputation in the mass public.
RoPRA gratefully acknowledges financial support from Analytics at Wharton.