Researchers at the Stanford Computational Policy Lab have a clever paper that looks at racial profiling by police in traffic stops. The analysis compares racial disparities in traffic stops during the day time-when it is relatively easier to determine the race of a driver-compared to racial disparities in night time stops when it is more difficult to do so,
To assess racial disparities in police interactions with the public, we compiled and analyzed a dataset detailing nearly 100 million municipal and state patrol traffic stops conducted in dozens of jurisdictions across the country—the largest such effort to date. We analyze these records in three steps. First, we measure potential bias in stop decisions by examining whether black drivers are less likely to be stopped after sunset, when a “veil of darkness” masks one’s race. After adjusting for time of day—and leveraging variation in sunset times across the year—we find evidence of bias against black drivers both in highway patrol and in municipal police stops. Second, we investigate potential bias in decisions to search stopped drivers. Examining both the rate at which drivers are searched and the likelihood that searches turn up contraband, we find evidence that the bar for searching black and Hispanic drivers is lower than for searching whites. Finally, we examine the effects of legalizing recreational marijuana on policing in Colorado and Washington state. We find evidence that legalization reduced the total number of searches conducted for both white and minority drivers, but we also find that the bar for searching minority drivers is still lower than for whites postlegalization. We conclude by offering recommendations for improving data collection, analysis, and reporting by law enforcement agencies.