An Analysis of the New York City Police Department's “Stop-and-Frisk” Policy in the Context of Claims of Racial Bias

By Andrew Gelman, Jeffrey A. Fagan, Alex Kiss. 2007

819 citations recorded by the source corpus.

Subfields: Health, Political Science and International Relations, Sociology and Political Science

View Paper: https://www.semanticscholar.org/paper/f07bdc667967ba5f0884a0b9835fba3098f1c5e1

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Health

In Political Science and International Relations

In Sociology and Political Science

Citations in the corpus

Auditing Black-Box Models Using Transparent Model Distillation With Side Information (2017, background): “The New York Police Department’s stop-and-frisk data12 has been scrutinized for racial bias [13, 20].”
Does Predictive Policing Lead to Biased Arrests? Results From a Randomized Controlled Trial (2018, background): “pedestrian stops [18, 19, 25, 26, 27, 49, 59], traffic tickets [16], drug enforcement and arrests [7, 9, 33, 38, 57], use of force [45, 13, 35, 51], and even in the decision to shoot white or black criminal suspects while in a training simulator [24, 47].”
Race and Perceptions of Police: Experimental Results on the Impact of Procedural (In)Justice (2017, neutral): “Using stop-and-frisk data from the New York City Police Department, for example, Gelman, Fagan, and Kiss (2007, p. 813) found that African American and Hispanic pedestrians were more likely than whites to be stopped, “even after controlling for precinct variability and race-speciﬁc estimates of…”
Fairness through Causal Awareness: Learning Causal Latent-Variable Models for Biased Data (2018, background): “Furthermore, the sensitive attribute can causally effect the outcome as well; research has shown that policing can disparately effect various races, even controlling for police presence [14] (the treatment in this case).”
Fast Threshold Tests for Detecting Discrimination (2017, result): “Our findings bolster past studies of New York City’s stopand-frisk practices (Goel et al., 2016; Gelman et al., 2007), which came to similar conclusions, but did not account for potential infra-marginality.”
The Problem of Infra-marginality in Outcome Tests for Discrimination (2016, methodology): “Studying police stops of pedestrians in New York City, Gelman et al. (2007) use a hierarchical Bayesian model to construct a benchmark based on neighborhood- and race-specific crime rates.”
A Hierarchy of Limitations in Machine Learning (2020, background): “For example, why should quantitative evidence (e.g., Gelman et al., 2007), rather than people’s lived experience, be the arbiter of whether or not policing is biased?”
A multidisciplinary survey on discrimination analysis (2013, methodology): “Using a data set of stops by the New York Police Department (NYPD), Gelman et al. (2007) found that, after controlling for population distribution and crime distribution for violent crimes and weapons offenses, blacks and Hispanics are subject to ‘stop-and-frisk’ about twice as often as whites. To h”