Working Paper: NBER ID: w18803
Authors: Decio Coviello; Nicola Persico
Abstract: We analyze data on NYPD's "stop and frisk program" in an effort to identify racial bias on the part of the police officers making the stops. We find that the officers are not biased against African Americans relative to whites, because the latter are being stopped despite being a "less productive stop" for a police officer.
Keywords: No keywords provided
JEL Codes: K42
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| NYPD officers are not biased against African Americans (J15) | whites are stopped despite being a less productive stop for officers (J79) |
| whites are stopped despite being a less productive stop for officers (J79) | arrest rate for whites is marginally lower than for blacks (K42) |
| race of the pedestrian (R41) | likelihood of arrest (K42) |
| lack of bias is supported by the absence of significant differences in arrest rates when controlling for precinct fixed effects (J79) | observed differences in arrest probabilities do not demonstrate racial bias (J15) |