Stop and Frisk: NYPD
Kyrah Peterson
2024-11-22
Section 1: Introduction
In this project, I will be examining stop, question and frisk data from the New York Police Department in 2022. Some questions I will be answering are as follows:
Question 1. What is the racial and gender distribution of individuals who were stopped and frisked by the police in 2022? Are there any disparities in stop-and-frisk encounters based on race or gender?
Question 2. How have the number of stop-and-frisk encounters changed over the months of 2022? Are there specific days of the week or times of day when stop-and-frisk incidents are more common?
Question 3. What are the most common reasons cited by police officers for conducting stop-and-frisk encounters? Is there a relationship between the stated reason for the stop and the outcome of the encounter?
Question 4. What percentage of stop-and-frisk encounters result in arrests, summonses, or other outcomes? Are there differences in outcomes based on the demographics of the individuals stopped?
Question 5. Which neighborhoods or precincts have the highest number of stop-and-frisk incidents? Is there a correlation between the location of stops and the demographic characteristics of the population?
Question 6. How frequently do police officers find weapons or contraband during stop-and-frisk encounters? Is there a connection between weapon or contraband discovery and the reasons for stops?
Question 7. How many individuals have been stopped and frisked multiple times in 2022? Are there any patterns in the demographics or outcomes of repeat encounters?
Question 8. Is there a relationship between the age of individuals and their likelihood of being stopped and frisked? How do the reasons for stops differ across age groups?
Question 9. Which police officers have conducted the highest number of stop-and-frisk encounters? Are there variations in outcomes based on the officers involved?
Question 10. How does the stop-and-frisk data from 2022 compare to previous years in terms of overall numbers and demographic distributions? Have there been any changes in stop-and-frisk practices or outcomes over time?
Below, a portion of the data I will be using is shown.
## STOP_ID STOP_FRISK_DATE STOP_FRISK_TIME YEAR2 MONTH2 DAY2
## 1 1 1/1/22 8:40:00 2022 January Saturday
## 2 2 1/1/22 3:25:00 2022 January Saturday
## 3 3 1/1/22 0:19:00 2022 January Saturday
## 4 4 1/1/22 3:00:00 2022 January Saturday
## 5 5 1/1/22 3:00:00 2022 January Saturday
## 6 6 1/1/22 10:30:00 2022 January Saturday
## STOP_WAS_INITIATED RECORD_STATUS_CODE ISSUING_OFFICER_RANK
## 1 Based on Self Initiated APP POM
## 2 Based on Self Initiated APP POM
## 3 Based on Self Initiated APP POF
## 4 Based on Radio Run APP POM
## 5 Based on Radio Run APP POM
## 6 Based on C/W on Scene APP POM
## ISSUING_OFFICER_COMMAND_CODE SUPERVISING_OFFICER_RANK
## 1 73 LT
## 2 183 SGT
## 3 52 LT
## 4 9 LT
## 5 9 LT
## 6 47 SGT
## SUPERVISING_OFFICER_COMMAND_CODE
## 1 73
## 2 183
## 3 183
## 4 9
## 5 9
## 6 47
## SUPERVISING_ACTION_CORRESPONDING_ACTIVITY_LOG_ENTRY_REVIEWED
## 1 Y
## 2 Y
## 3 Y
## 4 N
## 5 N
## 6 Y
## LOCATION_IN_OUT_CODE JURISDICTION_CODE JURISDICTION_DESCRIPTION
## 1 O P PSB
## 2 (null) (null) (null)
## 3 (null) (null) (null)
## 4 (null) P PSB
## 5 (null) (null) (null)
## 6 (null) (null) (null)
## OBSERVED_DURATION_MINUTES SUSPECTED_CRIME_DESCRIPTION STOP_DURATION_MINUTES
## 1 1 CPW 4
## 2 1 CPW 1
## 3 1 CPW 1
## 4 5 ASSAULT 10
## 5 5 ASSAULT 10
## 6 5 CPW 40
## OFFICER_EXPLAINED_STOP_FLAG OFFICER_NOT_EXPLAINED_STOP_DESCRIPTION
## 1 Y (null)
## 2 Y (null)
## 3 Y (null)
## 4 Y (null)
## 5 Y (null)
## 6 Y (null)
## OTHER_PERSON_STOPPED_FLAG SUSPECT_ARRESTED_FLAG SUSPECT_ARREST_OFFENSE
## 1 N Y CPW
## 2 N Y CPW
## 3 N Y CPW
## 4 Y N (null)
## 5 Y N (null)
## 6 N N (null)
## SUMMONS_ISSUED_FLAG SUMMONS_OFFENSE_DESCRIPTION OFFICER_IN_UNIFORM_FLAG
## 1 N (null) Y
## 2 N (null) Y
## 3 N (null) Y
## 4 N (null) Y
## 5 N (null) Y
## 6 Y OTHER Y
## ID_CARD_IDENTIFIES_OFFICER_FLAG SHIELD_IDENTIFIES_OFFICER_FLAG
## 1 (null) (null)
## 2 (null) (null)
## 3 (null) (null)
## 4 (null) (null)
## 5 (null) (null)
## 6 (null) (null)
## VERBAL_IDENTIFIES_OFFICER_FLAG FRISKED_FLAG SEARCHED_FLAG ASK_FOR_CONSENT_FLG
## 1 (null) Y Y N
## 2 (null) Y Y N
## 3 (null) N Y (null)
## 4 (null) N N N
## 5 (null) N N N
## 6 (null) Y N N
## CONSENT_GIVEN_FLG OTHER_CONTRABAND_FLAG FIREARM_FLAG KNIFE_CUTTER_FLAG
## 1 N N Y (null)
## 2 N N Y (null)
## 3 (null) N Y (null)
## 4 N N (null) (null)
## 5 N N (null) (null)
## 6 N N (null) (null)
## OTHER_WEAPON_FLAG WEAPON_FOUND_FLAG PHYSICAL_FORCE_CEW_FLAG
## 1 (null) Y (null)
## 2 (null) Y (null)
## 3 (null) Y Y
## 4 (null) N (null)
## 5 (null) N (null)
## 6 (null) N (null)
## PHYSICAL_FORCE_DRAW_POINT_FIREARM_FLAG PHYSICAL_FORCE_HANDCUFF_SUSPECT_FLAG
## 1 (null) (null)
## 2 (null) (null)
## 3 (null) Y
## 4 (null) (null)
## 5 (null) (null)
## 6 (null) (null)
## PHYSICAL_FORCE_OC_SPRAY_USED_FLAG PHYSICAL_FORCE_OTHER_FLAG
## 1 (null) (null)
## 2 (null) (null)
## 3 (null) (null)
## 4 (null) (null)
## 5 (null) (null)
## 6 (null) (null)
## PHYSICAL_FORCE_RESTRAINT_USED_FLAG PHYSICAL_FORCE_VERBAL_INSTRUCTION_FLAG
## 1 (null) Y
## 2 (null) Y
## 3 (null) (null)
## 4 (null) Y
## 5 (null) Y
## 6 (null) Y
## PHYSICAL_FORCE_WEAPON_IMPACT_FLAG BACKROUND_CIRCUMSTANCES_VIOLENT_CRIME_FLAG
## 1 (null) (null)
## 2 (null) (null)
## 3 (null) (null)
## 4 (null) (null)
## 5 (null) (null)
## 6 (null) Y
## BACKROUND_CIRCUMSTANCES_SUSPECT_KNOWN_TO_CARRY_WEAPON_FLAG
## 1 (null)
## 2 (null)
## 3 (null)
## 4 (null)
## 5 (null)
## 6 (null)
## SUSPECTS_ACTIONS_CASING_FLAG
## 1 (null)
## 2 (null)
## 3 (null)
## 4 (null)
## 5 (null)
## 6 (null)
## SUSPECTS_ACTIONS_CONCEALED_POSSESSION_WEAPON_FLAG
## 1 Y
## 2 Y
## 3 Y
## 4 (null)
## 5 (null)
## 6 Y
## SUSPECTS_ACTIONS_DECRIPTION_FLAG SUSPECTS_ACTIONS_DRUG_TRANSACTIONS_FLAG
## 1 (null) (null)
## 2 (null) (null)
## 3 (null) (null)
## 4 Y (null)
## 5 Y (null)
## 6 Y (null)
## SUSPECTS_ACTIONS_IDENTIFY_CRIME_PATTERN_FLAG SUSPECTS_ACTIONS_LOOKOUT_FLAG
## 1 (null) (null)
## 2 (null) (null)
## 3 (null) (null)
## 4 (null) (null)
## 5 (null) (null)
## 6 (null) (null)
## SUSPECTS_ACTIONS_OTHER_FLAG SUSPECTS_ACTIONS_PROXIMITY_TO_SCENE_FLAG
## 1 (null) (null)
## 2 (null) (null)
## 3 (null) (null)
## 4 (null) (null)
## 5 (null) (null)
## 6 Y Y
## SEARCH_BASIS_ADMISSION_FLAG SEARCH_BASIS_CONSENT_FLAG
## 1 Y (null)
## 2 (null) (null)
## 3 (null) (null)
## 4 (null) (null)
## 5 (null) (null)
## 6 (null) (null)
## SEARCH_BASIS_HARD_OBJECT_FLAG SEARCH_BASIS_INCIDENTAL_TO_ARREST_FLAG
## 1 Y (null)
## 2 (null) Y
## 3 (null) Y
## 4 (null) (null)
## 5 (null) (null)
## 6 (null) (null)
## SEARCH_BASIS_OTHER_FLAG SEARCH_BASIS_OUTLINE_FLAG
## 1 (null) Y
## 2 (null) (null)
## 3 (null) (null)
## 4 (null) (null)
## 5 (null) (null)
## 6 (null) (null)
## DEMEANOR_OF_PERSON_STOPPED SUSPECT_REPORTED_AGE
## 1 FLED ON FOOT 21
## 2 #N/A 25
## 3 NERVOUS CHANGING DIRECTION FROM OFFICERS RUNNING 15
## 4 CALM 34
## 5 CALM 28
## 6 HOSTILE 30
## SUSPECT_SEX SUSPECT_RACE_DESCRIPTION SUSPECT_HEIGHT SUSPECT_WEIGHT
## 1 MALE BLACK 5.11 195
## 2 MALE BLACK 5.1 165
## 3 MALE BLACK 5.3 120
## 4 MALE BLACK HISPANIC 5.9 150
## 5 MALE WHITE 5.9 160
## 6 MALE BLACK 6.4 (null)
## SUSPECT_BODY_BUILD_TYPE SUSPECT_EYE_COLOR SUSPECT_HAIR_COLOR
## 1 U BRO BLK
## 2 MED BRO BLK
## 3 THN BRO BLK
## 4 (null) BRO BLK
## 5 (null) BRO BLK
## 6 THN BLK BRO
## SUSPECT_OTHER_DESCRIPTION STOP_LOCATION_PRECINCT STOP_LOCATION_SECTOR_CODE
## 1 (null) 73 C
## 2 (null) 42 A
## 3 N/A 42 A
## 4 (null) 9 A
## 5 (null) 9 A
## 6 (null) 47 B
## STOP_LOCATION_APARTMENT STOP_LOCATION_FULL_ADDRESS
## 1 (null) LIVONIA AVENUE && THATFORD AVENUE
## 2 (null) WASHINGTON AVE && E 171 ST
## 3 (null) E 170 ST && PARK AVE
## 4 (null) AVENUE A && E 1 ST
## 5 (null) AVENUE A && E 1 ST
## 6 (null) E 234 ST && KATONAH AVE
## STOP_LOCATION_STREET_NAME STOP_LOCATION_X STOP_LOCATION_Y
## 1 LIVONIA AVENUE 1008275 183622
## 2 WASHINGTON AVE 1010997 244468
## 3 E 170 ST 1010321 243768
## 4 AVENUE A 988051 202409
## 5 AVENUE A 988051 202409
## 6 E 234 ST 1021001 266076
## STOP_LOCATION_PATROL_BORO_NAME STOP_LOCATION_BORO_NAME
## 1 PBBN BROOKLYN
## 2 PBBX BRONX
## 3 PBBX BRONX
## 4 PBMS MANHATTAN
## 5 PBMS MANHATTAN
## 6 PBBX BRONXSection 2: Demographic analysis
Section 2.1: Racial and Gender Distribution
##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union## # A tibble: 22 × 4
## SUSPECT_RACE_DESCRIPTION SUSPECT_SEX count percentage
## <chr> <chr> <int> <dbl>
## 1 (null) (null) 97 0.642
## 2 (null) FEMALE 8 0.0530
## 3 (null) MALE 87 0.576
## 4 AMERICAN INDIAN/ALASKAN NATIVE FEMALE 4 0.0265
## 5 AMERICAN INDIAN/ALASKAN NATIVE MALE 21 0.139
## 6 ASIAN / PACIFIC ISLANDER FEMALE 22 0.146
## 7 ASIAN / PACIFIC ISLANDER MALE 298 1.97
## 8 BLACK (null) 22 0.146
## 9 BLACK FEMALE 616 4.08
## 10 BLACK MALE 8225 54.5
## # ℹ 12 more rowsThis table displays the counts and percentages of stop and frisk subjects by race and gender.
Section 2.2: Percentage Distribution
This bar plot displays the distribution of stop and frisk suspects by gender and race. Based on this plot, it appears there is a large disparity in the number of black men who are subjected to stop and frisks by the NYPD.
Section 3: Temporal Trends
Section 3.1: Trends in Stop and Frisk by Month
##
## Attaching package: 'lubridate'## The following objects are masked from 'package:base':
##
## date, intersect, setdiff, union
This scatterplot displays the stop and frisk encounters by month for the year 2022. Based on this plot, it appears that stop and frisk encounters are the highest in March, April and May, after which they decline until July. After July, encounters increase until October, and the steeply decline and reach a minimum in December.
Section 3.2: Trends in Stop and Frisk by Day of the Week
This scatterplot displays stop and frisk encounters by day of the week. Stop and frisks are most likely to occur on Wednesday, and least likely to occur on Monday.
Section 3.3: Trends in Stop and Frisk by Time of Day
This scatterplot displays stop and frisk encounters by hour of the day. Stop and frisk enounters are at a minimum between 5 and 6 AM, and then increase from about 7AM until 12AM. Encounters are at a maximum at around 11PM.
Section 4: Reasons for Stops
Section 4.1: Most Common Reasons for Stops
## # A tibble: 26 × 2
## SUSPECTED_CRIME_DESCRIPTION Count
## <chr> <int>
## 1 CPW 6908
## 2 ROBBERY 1544
## 3 PETIT LARCENY 1336
## 4 ASSAULT 1269
## 5 BURGLARY 1077
## 6 OTHER 557
## 7 GRAND LARCENY 439
## 8 GRAND LARCENY AUTO 434
## 9 MENACING 414
## 10 CRIMINAL MISCHIEF 238
## # ℹ 16 more rowsHere, a table with reasons for the stop and their counts are shown. Criminal posession of a weapon appears to be the most common reason for a stop, with a count of 6908 in 2022.
This bar graph visualizes the top 10 most common reasons for a stop to help better understand the distribution.
Section 4.2: Relationship Between Stop Reasons and Outcomes
This bar plot displays the rates for summons and arrest for the top 10 most common reasons for a stop. Summons appear to be relatively low for all of the crimes, but is the highest for the stop reason “other”. Arrest rates are highest for petty larceny, which is a theft of property worth less than $1,000. The crime with the lowest arrest rate is criminal posession of a weapon, even though it is the most common reason for a stop.
Section 5: Outcomes of Stops
Section 5.1: Stop and Frisk Percentages for Outcomes
This bar graph displays the percentage of stop and frisk encounters that resulted in an arrest, a summons, or other. Roughly 33% of stops resulted in an arrest, 3% resulted in a summons, and 64% resulted in “other”. The “other” category was calculated by subtracting the number of arrests and summons from the total number of stops.
Section 5.2: Differences in Outcomes by Demographics
Here, a bar graph breaks down stop outcomes by race. The most common
result among all races is “other”, with Middle Eastern/Southwest Asian
most commonly receiving this outcome. Arrest outcomes are most common in
white suspects.
Section 6: Location Analysis
Section 6.1: Neighborhoods/Precincts with the Highest Stop and Frisk Encounters
This bar graph displays the number of stop and frisk encounters by
neighborhood. The Bronx and Brooklyn have the highest stop rates, while
Staten Island has the lowest.
Section 6.2: Correlation Between Stop Location and Demographic
## Warning in chisq.test(chisq_test): Chi-squared approximation may be incorrect##
## Pearson's Chi-squared test
##
## data: chisq_test
## X-squared = 1697.4, df = 28, p-value < 2.2e-16The results of a Chi-Squared test for race and neighborhood are shown above. The resulting p-value is very low, meaning that the data supports the alternative hypothesis that race and neighborhood are correlated in terms of stop and frisk encounters.
This bar plot displays the number of stop and frisk encounters by race for each neighborhood. In all neighborhoods, black people are the most likely to be stopped, and American Indian/Alaskan Native are the least likely.
Section 7: Weapon and Contraband Discovery
Section 7.1: Frequency of Finding Weapons or Contraband
This bar graph displays the frequency of finding a weapon (firearm, knife, or other) or contraband in a stop. Out of 15,102 encounters, firearms were found 1,187 times, knives were found 1,083 times, other weapons were found 265 times, and contraband was found 875 times.
Section 7.2: Connection Between Weapon/Contraband Discovery and Reason for Stop
The graph above displays the connection between crime/reason for stop, and the discovery of weapons or contraband. The highest instance of discovery of a weapon or contraband is for the crime of criminal posession of a weapon. Most commonly in these encounters, the criminal was found with a firearem.
Section 8: Repeat Encounters
Unfortunately, with the data provided, there is no way to identify which people were encountered in a stop and frisk more than once in 2022. To be able to do this, there would need to be a column in the data that uniquely identifies each criminal with information like name and date of birth.
Section 9: Age and Stop Frequency
Section 9.1: Likelihood of Being Stopped by Age
## Warning: NAs introduced by coercion## Warning: Removed 1 row containing missing values or values outside the scale range
## (`geom_point()`).
This scatterplot displays the distribution of stop and frisk encounters by age. The number of stops increases from age 13 to 17, peaks around age 17, and then gradually decreases.
Section 9.2: Most common Reasons for Stops by Age Group
The bar graph above displays the most common reason for a stop for each age in the data. It appears the most common reason for a stop between the ages of 13 to 40 is criminal possession of a weapon. After age 40, the reason for stops becomes more diverse and is most commonly petty larceny.
Section 10: Officer Identification
Section 10.1: Officers with Highest Stop and Frisk Counts
## # A tibble: 10 × 2
## ISSUING_OFFICER_RANK Num_Stops
## <chr> <int>
## 1 "POM" 12383
## 2 "POF" 1615
## 3 "SGT" 424
## 4 "DTS" 330
## 5 "DT3" 143
## 6 "LT " 123
## 7 "CPT" 28
## 8 "LSA" 20
## 9 "DI " 17
## 10 "SSA" 9This table displays which officers had the most stop and frisk encounters. By a large margin, male police officers had the most stop and frisk encounters. Of 15,102 stops, 12,383 stops were made by male police officers, which is roughly 82% of stops.
Section 10.2: Outcomes Based on the Officer Involved
This stacked bar chart shows the variation in outcomes for each type of officer. Based on the chart, the least likely outcome from a stop is a summons, and an arrest or “other” seem to be almost evenly split among all officers. DI and SSA officers did not issue any summons during the year of 2022.