Good Cop, Bad Cop: Using Civilian Allegations to Predict Police Misconduct
利用芝加哥平民投诉和民权诉讼数据，采用经验贝叶斯方法评估平民投诉对警察严重不当行为的预测价值，发现投诉能有效识别最差警员，为干预提供依据。
In response to high-profile cases of police misconduct, reformers are calling for greater use of civilian allegations in identifying potential problem officers. This paper applies an Empirical Bayes framework to data on civilian allegations and civil rights litigation in Chicago to assess the predictive value of civilian allegations for serious future misconduct. We find a strong relationship between allegations and future civil rights litigation, especially for the very worst officers. The worst 1 percent of officers, as measured by civilian allegations, generate almost 5 times the number of payouts and over 4 times the total damage payouts in civil rights litigation. These findings suggest that intervention efforts could be fruitfully concentrated among a relatively small group.