Abstract
Objectives
This study derives the statistical power of the common hit rates test of taste-based discrimination in police searches. It also identifies search intensity as a source of bias in the test and proposes a simple empirical adjustment to account for the bias.
Methods
Data simulations, along with two empirical applications to motor vehicle search data, display the practical importance of both statistical power and search intensity bias in the hit rates test.
Results
Statistical power varies markedly with the parameters of the application. Differential search intensity across groups will bias results, but the simple empirical adjustment provides a valid test when the data contain a discrete indicator of search intensity. In the empirical applications, unadjusted and adjusted tests differ in their conclusion of whether police discrimination exists.
Conclusions
For the presentation of multiple hit rates tests, statistical power should be reported with p-values. Theoretical bounds on search intensity bias are wide, and the bias can persist for any sample size. Hit rates tests should therefore be interpreted with caution when data contain no indicator of search intensity.
Similar content being viewed by others
Notes
This terminology differs from Knowles et al. (2001), who use intensity to describe the rate at which police search a group.
Another way to interpret \(\omega\) is via the square root of the noncentrality parameter divided by the sample size.
If the crime rate appears high, recall the population contains only searches, not all citizens. Alternatively, a lower crime rate and higher detection rate would generate results very similar to the current scenario.
The data also contain information on passenger searches. For the purpose of the application, those searches are excluded because traffic stops with passengers may not provide a valid comparison of traffic stops without passengers.
References
Alesina A, La Ferrara E (2014) A test of racial bias in capital sentencing. Am Econ Rev 104(11):3397–3433
Antonovics K, Knight BG (2009) A new look at racial profiling: evidence from the Boston Police Department. Rev Econ Stat 91(1):163–177
Anwar S, Fang H (2006) An alternative test of racial prejudice in motor vehicle searches: theory and evidence. Am Econ Rev 96(1):127–151
Anwar S, Fang H (2015) Testing for racial prejudice in the parole board release process: theory and evidence. J Legal Stud 44(1):1–37
Ayres I (2002) Outcome tests of racial disparities in police practices. Justice Res Policy 4(1–2):131–142
Baumgartner FR, Epp DA, Shoub K (2018) Suspect citizens: what 20 million traffic stops tell us about policing and race. Cambridge University Press, Cambridge
Becker GS (1957) The economics of discrimination. Chicago University Press, Chicago
Bjerk D (2007) Racial profiling, statistical discrimination, and the effect of a colorblind policy on the crime rate. J Public Econ Theory 9(3):521–546
Camelia S, Corbett-Davies S, Goel S (2017) The problem of infra-marginality in outcome tests for discrimination. Ann Appl Stat 11(3):1193–1216
Cohen J (1998) Statistical power analysis for the behavioral sciences. Lawrence Erlbaum Associates Publishers, Hillsdale, NJ
Coviello D, Persico N (2015) An economic analysis of black-white disparities in the New York police departments stop-and-frisk program. J Legal Stud 44(2):315–360
Dharmapala D, Ross SL (2004) Racial bias in motor vehicle searches: additional theory and evidence. BE J Econ Analy Policy 3(1):1–23
Engel RS (2008) A critique of the ”outcome test” in racial profiling research. Justice Q 25(1):1–36
Engel RS, Tillyer R (2008) Searching for equilibrium: the tenuous nature of the outcome test. Justice Q 25(1):54–71
Fridell LA (2004) By the numbers: a guide for analyzing race data from vehicle stops. Police Executive Research Forum, Washington, DC
Gelman A, Fagan J, Kiss A (2007) An analysis of New York City police department’s ”Stop-and-Frisk” police in the context of claims of racial bias. J Am Stat Assoc 102:813–823
Gramlich J (2019) From police to parole, black and white Americans differ widely in their views of criminal justice system. Pew Res Center
Grogger J, Ridgeway G (2006) Testing for racial profiling in traffic stops from behind a veil of darkness. J Am Stat Assoc 101(475):878–887
Gross SR, Barnes KY (2002) Road work: racial profiling and drug interdiction on the highway. Mich Law Rev 101(3):651–754
Heaton P (2010) Understanding the effects of antiprofiling policies. J Law Ec 53(1):29–64
Hernández-Murillo R, Knowles J (2004) Racial profiling or racist policing? Bounds tests in aggregate data. Int Econ Rev 45(3):2959–989
Knowles J, Persico N, Todd P (2001) Racial bias in motor vehicle searches: theory and evidence. J Polit Econ 109(1):203–229
Lehrer S, Lepage L (2019) Does selective crime reporting influence our ability to detect racial discrimination in the NYPD’s Stop-and-Frisk Program? In: the econometrics of complex survey data (Adv. in Econometrics, Vol. 39), Emerald Publishing Limited: 259–286
Maclin T (2008) The Good and bad news about consent searches in the Supreme Court. McGeorge Law Rev 39(1):27–82
Mungan M (2020) Discrimination and deterrence with enforcer liability. Am Law Econ Rev forthcoming
Persico N, Todd P (2006) Generalising the hit rates test for racial bias in law enforcement, with an application to vehicle searches in Wichita. Econ J 116(515):F357–F367
Persico N, Todd P (2008) The hit rates test for racial bias in motor vehicle searches. Justice Q 25(1):37–53
Pierson E, Simoiu C, Overgoor J, Corbett-Davies S, Jenson D, Shoemaker A, Ramachandran V, Barghouty P, Phillips C, Shroff R, Goel S (2020) A large-scale analysis of racial disparities in police stops across the United States. Nat Hum Behav 4:736–745
Ritter JA (2017) How do police use race in traffic stops and searches? Tests based on the observability of race. J Econ Behav Organ 135:82–98
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix
Appendix
A.1 Proofs
Proof of Result 1
From (5),
takes on the sign of its numerator.
Suppose \(\delta \ge 0\). The numerator is positive if and only if
Recall that \(\gamma +\delta \le 1\). Then
and the middle inequality holds for \(p \in (0,1)\). Thus, condition (C1) holds for \(\delta \ge 0\).
Suppose \(\delta <0\). The numerator is now negative if and only if condition (C1) holds. Rewrite (C1) as
If \(\gamma \ge 1/2\), the right-hand side is weakly negative, and the left-hand side is strictly positive, so the inequality holds. If \(\gamma < 1/2\), then \((1-\gamma ) > (2\gamma - 1)\). Also, \(2 > (1-p)\), and \(\gamma \ge | \delta |\) because \(\gamma + \delta \ge 0\). Thus, (C1) holds for \(\delta <0\). \(\square\)
Proof of Result 2
From (5),
and
the latter of which is the sum of two positive terms. \(\Omega (\delta ,\gamma ,p)\) is therefore convex in \(\gamma\). Solving the first-order condition,
\(\square\)
Proof of Result 3
First, rewrite (5) as
Then
where
Further, define
Then
where the last equality follows after copious algebra.
Note that
For \(\delta \ge 0\), \(\gamma +\delta \le 1\), so \(1-\gamma \ge \delta\) and \(1-\delta \ge \gamma\). Then
For \(\delta < 0\),
But \(\delta < 0\) implies \(\gamma +\delta \ge 0\), so \(\gamma \ge -\delta\). Then
Thus, \(\lambda >0\) unless \(\gamma =|\delta |=1/2\). Recall that \(\Psi =(1-\gamma _u)\gamma _u>0\). Therefore,
Because \(p(1-p)\) is maximized at \(p=1/2\),
so \(\Omega (\delta ,\gamma ,p)\) is strictly concave in p.
Next, define
If \(\delta +2\gamma =1\), then \(p^*=1/2\). Otherwise, the first-order condition yields
Recall \(\lambda \ge 0\). The term under the square root is weakly positive if
which is true by assumption, so \(p^*\) is a real number.
Suppose \(\delta >0\). Then
For \(\delta + 2\gamma > 1\), the only positive solution to the quadratic formula is
which is strictly less than one if and only if
Again, the last inequality holds by assumption.
For \(\delta + 2 \gamma < 1\), both solutions to the quadratic formula are positive, but
The other solution is strictly less than one if and only if
Thus, if \(\delta > 0\) (and \(\delta + 2 \gamma \ne 1\)),
Now suppose \(\delta < 0\). Then
Similar arguments again yield a unique solution of
\(\square\)
A.2 Power in the Case of Three Groups
Figures 5, 6, 7 display power as a function of the parameters in a hit rates test of three groups. A reference group has baseline hit rate \(\gamma\). For groups one and two, the differences in hit rates from the baseline are denoted by \(\delta _1\) and \(\delta _2\), respectively. The proportion of searches in groups one and two are denoted by \(p_1\) and \(p_2\).
A.4 Simulation with an Expanded Sample Size
See Fig. 8
A.5 The Hit Rates Model with a Resource Constraint on Intensive Searches
Consider the classical hit rates of model of Knowles et al. (2001) with a binary, intensive search technology. (The description here is somewhat informal.) For a continuum of police officers and motorists, let \(r \in \{B,W\}\) denote the race of the motorist, and let \(c \in \mathbb {R}\) denote other characteristics an officer may use in the decision to search a vehicle. The notation for c matches that of the classical model and should not be confused with the crime rate in the discussion above. Race is everywhere observable. The officer observes c, but the econometrician may not observe c, which follows distribution function F(c|r).
Officers choose whether to search a motorist of type (c, r). They have access to a binary search technology, \(b \in \{0,1\}\). If they search a guilty motorist without the technology, they detect the crime with probability d. With the technology, they raise the probability of detection to \(d+\phi\). Officers maximize total convictions subject to the cost of search. The marginal cost of searching a motorist of race r without the technology is \(t_r\). Police discrimination operates when \(t_B \ne t_W\). An arrest provides a normalized benefit equal to one, so cost is scaled as a fraction of the benefit. Assume \(t_r \le d\), i.e., a search would always be worth conducting if every motorist carries contraband.
Motorists decide whether to carry contraband. If they do not carry, they obtain a zero payoff. If they do carry, they obtain \(-j(c,r)\) if the crime is detected and v(c, r) if the crime is not detected. Both j(c, r) and v(c, r) are strictly positive.
Let \(\mu ^b(c,r)\) denote the probability an officer searches a motorist of type (c, r) with technology b. The expected payoff to contraband is
A motorist will carry contraband if and only if the expected payoff is greater than zero. If the payoff is exactly zero, motorists are indifferent and may randomize over whether to carry. Denote the probability a motorist of type (c, r) is guilty by P(G|c, r).
Officers choose search probabilities to solve
where M denotes a resource constraint on the use of intensive searches. In any equilibrium with a positive crime rate, the resource constraint will bind.
For a motorist to optimally randomize,
Define
If the same characteristics have the same ordinal relationship to u(c, r) for both races, then reorder c so u(c, r) is increasing. Assume
Define \(\bar{c}_r\) as the solution to
Let u(c, r) follow distribution function H(c, r). If \(H(\bar{c}_r,r)<1\), then some motorists of race r will not be deterred even when \(\mu ^1(c,r)=1\).
First, suppose \(H(\bar{c}_r,r)=1\) for both races. Suppose officers are unbiased, so \(t_B=t_W=t\). If \(P^*(G|c,r)>t/d\), then \(\mu ^0(c,r)+\mu ^1(c,r)=1\), and the randomization condition for motorists is violated. If \(P^*(G|c,r)<t/d\), then \(\mu ^0(c,r)=0\) and \(\mu ^1(c,r)=u(c,r)/(d+\phi )\) for all (c, r), but the latter equality is negated by a sufficiently binding resource constraint. Furthermore, an equilibrium of exclusively intensive searches would be incompatible with observational data. Thus, \(P^*(G|c,r)=t/d\).
The equality of crime rates in equilibrium provides the basis for a test of police bias. Hit rates for each race are
Because \(P^*(G|c,r)=t/d\) implies \(D(W)=D(B)\), the standard hit rates test applies irrespective of the search technology.
Now suppose \(H(\bar{c}_r,r)<1\) for at least one race. Police form correct beliefs on H(c, r) in equilibrium. For simplicity, take the case of
Up to the resource constraint, police intensively search motorists of each race with probability one when \(c \ge \bar{c}_r\). The division of intensive searches across race is arbitrary because the resource constraint binds before police enter the domain of deterrable motorists. (If the inequality did not hold, police would first intensively search non-deterrable motorists with probability one before randomizing with the leftover intensive search capacity as above.) For the remainder of motorists, equilibrium is analogous to the case of complete deterrability, and hit rates are
where, again, \(P^*(G|c,r)=t/d\). Then
The weighted difference in intensive searches should thus be subtracted from the difference in hit rates prior to any hit rates test. Because crime rates are equal in equilibrium, the subtraction is everywhere valid. It is necessary unless all crime is deterrable.
The adjusted difference in hit rates therefore offers a more accurate test of police bias when the econometrician does not observe all characteristics of every stop and search. The empirical adjustment for search intensity above can be calculated in any data set with a binary search technology. Lastly, when \(1 - H(\bar{c}_B,B) + 1 - H(\bar{c}_W,W) < M\), the adjustment is necessary only for motorists of type \(c \ge \bar{c}_r\), but the unobservability of that threshold is unproblematic since the adjustment is valid for all c.
Rights and permissions
About this article
Cite this article
Lundberg, A. Statistical Power and Search Intensity Bias in Hit Rates Tests of Discrimination. J Quant Criminol 38, 979–1002 (2022). https://doi.org/10.1007/s10940-021-09520-x
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10940-021-09520-x