The document discusses police shootings in America based on data from the Guardian and FiveThirtyEight databases. It finds that while over 2,100 people have been killed by police since 2015, only a small fraction of police departments report these killings. Predictive models attempting to classify whether victims were armed based on attributes like race, gender and poverty level performed poorly, reflecting the complexity of real-life situations. While public sentiment on Twitter was negative, more comprehensive data is still needed to fully understand potential police biases in shootings.
The goal of this project is to build a model using multiple linear regression that accurately predicts patterns between various socioeconomic factors that affect hate crime in the US before the 2016 US presidential elections and how these factors tied to the success of the president Donald Trump using MS Excel and SAS Studio.
CJ-4880 Police Brutality Increase in the unjustified .docxclarebernice
CJ-4880
Police Brutality: Increase in the unjustified use of force or in media coverage?
Introduction
Presently there has been an increase in attention on police forces around the United
States. It isn’t specifically centered in the areas typically known for crime or rogue police
officers, but it has hit home in the backyards of everyday Americans. These occasions of police
exercising force against citizens is plastering the media, and the coverage is endless. But the
question is about whether these officers are exercising their right to use force unjustly and truly
bringing fear into the hearts of Americans? Or is it the endless media coverage forcing it into the
lives of the people and using unsubstantiated facts to bring unnecessary damage to the officers
involved, the victims, and the general public? To answer these questions it is necessary to dive
into the minds of everyday citizens and the pure facts. This study intends to survey members of
the general public with specific age ranges with questions designed to provide information about
the perceptions of citizens and how they feel about police and the possibility of the increasing
occurrences of police brutality.
The Questions
Has police brutality truly increased and become a serious problem for the United States?
Are the officers who were meant to be serving and protecting destroying the trust in the police
forces? Or is the massive reach of the television giants reaching unjustified into the homes and
giving the public an incorrect assumption about the police? Few studies have directly answered
the above questions with most studies focusing on specific races in correlation of police brutality
and other focusing on rogue officers. This study is to focus on the possible correlation between
media coverage and the pubic believing that police brutality has increased. While the main
question is to determine whether the media has a direct effect on the opinion of officers, it is also
important to determine the facts about police brutality and bring those facts to the American
people to either change their perceptions or change the police. Those involved in this study will
play an important part to help the public reach an understanding about the facts of police
brutality and regain some trust in the law enforcement on the local and national levels.
Literature Review
The history of police brutality is deep and Americans are well versed in the stories of
Rodney King, Malice Green, and presently Michael Brown. Study after study has been
completed on police officers and racial discrimination but very few have focuses on the media
aspect. Police brutality is loosely defined as unethical behavior of a certified police officer who
uses excessive use of force, up to and including death. Public scrutiny of police use of force is
unavoidable (Alpert, 2009) The American public is expecting these officers to do their jobs with ...
Research Proposal Code#EB0011820201592277528Wordcount 1100 words.docxgholly1
Research Proposal Code#EB0011820201592277528
Wordcount 1100 words /4 pages
Urgency : 12 to 18 hours
Citation : APA
****************
The purpose of this assignment is to be in the role of an amateur researcher, coming up with a research question, and making decisions regarding what they are going to measure and how they are going to do it. Please provide complete answers to the following questions.
Answers should be single spaced, typed in 12pt Times New Roman, and no more than 2 pages.
1.
What is your research question?
Is there a difference between neighborhoods
where officer-involved shootings occur
and neighborhoods
where they do not occur
in terms of their level of social disorganization (measured as 0-100)? In other words, are officer-involved shootings more likely to occur in neighborhoods that are socially disorganized?
2.
Why did you choose this research question?
Officer-involved shootings have become a highly discussed topic in the aftermath of various high-profile killings of men of color. Understanding if a difference exists in the locations where these shootings occur, and where they do not, are important considerations in the officer’s decision to shoot. Places with high levels of social disorganization may lead an officer to be more likely to shoot (for several reasons that we will be unable to control for), whereas places with lower levels may make it less likely.
3.
Describe the dependent variable and the independent variable.
Dependent Variable
– The level of social disorganization, ratio, continuous
Independent Variable
– Census tracts, nominal, two categories
1. those that have experienced an OIS event,
2. those that have not experienced an OIS event.
4.
State the appropriate statistical test and explain why:
For my analysis, an
independent sample
t-test
is appropriate because my
independent variable is categorical
and my
dependent variable is continuous,
and I am
comparing two groups within the same variable
.
5.
State the null and alternative hypotheses:
H0: There
is no difference
between census tracts level of social disorganization based on if the census tract experienced an OIS event or not.
H1: There
is a difference
between census tracts which have experienced an OIS event and those that have not.
6.
Are there any other variables that you think will be related to the outcome? Describe at least 3 and explain why they are relevant.
1) Characteristics of police officers (sex, age, race, how many, etc.): Some officers may be less likely to use lethal force and controlling for that will lead to a stronger outcome.
2) Characteristics of suspects (sex, age, race, how many, did they have a weapon, etc.): Some characteristics of suspects may make officers more likely to shoot, whether they are legal factors or extra-legal factors.
3) Levels of firearm violence per neighborhood: neighborhoods which are at increased risk for firearm violence may make police more likely to per.
This report shows findings from a nationwide survey of Black men and police officers on the topic of racial bias in policing. The report also includes a detailed list of Verbatims from survey respondents.
The purpose of the study was to get opinions from those most impacted by the issue of racial bias in policing and to propose solutions.
This slideshow considers the privacy and ethical implication when dealing with criminal justice data. The dataset provided by the Bureau of Justice Statistics includes survey data from victims as well as compiles criminal stats. Issues with privacy are highlighted in this slideshare.
The goal of this project is to build a model using multiple linear regression that accurately predicts patterns between various socioeconomic factors that affect hate crime in the US before the 2016 US presidential elections and how these factors tied to the success of the president Donald Trump using MS Excel and SAS Studio.
CJ-4880 Police Brutality Increase in the unjustified .docxclarebernice
CJ-4880
Police Brutality: Increase in the unjustified use of force or in media coverage?
Introduction
Presently there has been an increase in attention on police forces around the United
States. It isn’t specifically centered in the areas typically known for crime or rogue police
officers, but it has hit home in the backyards of everyday Americans. These occasions of police
exercising force against citizens is plastering the media, and the coverage is endless. But the
question is about whether these officers are exercising their right to use force unjustly and truly
bringing fear into the hearts of Americans? Or is it the endless media coverage forcing it into the
lives of the people and using unsubstantiated facts to bring unnecessary damage to the officers
involved, the victims, and the general public? To answer these questions it is necessary to dive
into the minds of everyday citizens and the pure facts. This study intends to survey members of
the general public with specific age ranges with questions designed to provide information about
the perceptions of citizens and how they feel about police and the possibility of the increasing
occurrences of police brutality.
The Questions
Has police brutality truly increased and become a serious problem for the United States?
Are the officers who were meant to be serving and protecting destroying the trust in the police
forces? Or is the massive reach of the television giants reaching unjustified into the homes and
giving the public an incorrect assumption about the police? Few studies have directly answered
the above questions with most studies focusing on specific races in correlation of police brutality
and other focusing on rogue officers. This study is to focus on the possible correlation between
media coverage and the pubic believing that police brutality has increased. While the main
question is to determine whether the media has a direct effect on the opinion of officers, it is also
important to determine the facts about police brutality and bring those facts to the American
people to either change their perceptions or change the police. Those involved in this study will
play an important part to help the public reach an understanding about the facts of police
brutality and regain some trust in the law enforcement on the local and national levels.
Literature Review
The history of police brutality is deep and Americans are well versed in the stories of
Rodney King, Malice Green, and presently Michael Brown. Study after study has been
completed on police officers and racial discrimination but very few have focuses on the media
aspect. Police brutality is loosely defined as unethical behavior of a certified police officer who
uses excessive use of force, up to and including death. Public scrutiny of police use of force is
unavoidable (Alpert, 2009) The American public is expecting these officers to do their jobs with ...
Research Proposal Code#EB0011820201592277528Wordcount 1100 words.docxgholly1
Research Proposal Code#EB0011820201592277528
Wordcount 1100 words /4 pages
Urgency : 12 to 18 hours
Citation : APA
****************
The purpose of this assignment is to be in the role of an amateur researcher, coming up with a research question, and making decisions regarding what they are going to measure and how they are going to do it. Please provide complete answers to the following questions.
Answers should be single spaced, typed in 12pt Times New Roman, and no more than 2 pages.
1.
What is your research question?
Is there a difference between neighborhoods
where officer-involved shootings occur
and neighborhoods
where they do not occur
in terms of their level of social disorganization (measured as 0-100)? In other words, are officer-involved shootings more likely to occur in neighborhoods that are socially disorganized?
2.
Why did you choose this research question?
Officer-involved shootings have become a highly discussed topic in the aftermath of various high-profile killings of men of color. Understanding if a difference exists in the locations where these shootings occur, and where they do not, are important considerations in the officer’s decision to shoot. Places with high levels of social disorganization may lead an officer to be more likely to shoot (for several reasons that we will be unable to control for), whereas places with lower levels may make it less likely.
3.
Describe the dependent variable and the independent variable.
Dependent Variable
– The level of social disorganization, ratio, continuous
Independent Variable
– Census tracts, nominal, two categories
1. those that have experienced an OIS event,
2. those that have not experienced an OIS event.
4.
State the appropriate statistical test and explain why:
For my analysis, an
independent sample
t-test
is appropriate because my
independent variable is categorical
and my
dependent variable is continuous,
and I am
comparing two groups within the same variable
.
5.
State the null and alternative hypotheses:
H0: There
is no difference
between census tracts level of social disorganization based on if the census tract experienced an OIS event or not.
H1: There
is a difference
between census tracts which have experienced an OIS event and those that have not.
6.
Are there any other variables that you think will be related to the outcome? Describe at least 3 and explain why they are relevant.
1) Characteristics of police officers (sex, age, race, how many, etc.): Some officers may be less likely to use lethal force and controlling for that will lead to a stronger outcome.
2) Characteristics of suspects (sex, age, race, how many, did they have a weapon, etc.): Some characteristics of suspects may make officers more likely to shoot, whether they are legal factors or extra-legal factors.
3) Levels of firearm violence per neighborhood: neighborhoods which are at increased risk for firearm violence may make police more likely to per.
This report shows findings from a nationwide survey of Black men and police officers on the topic of racial bias in policing. The report also includes a detailed list of Verbatims from survey respondents.
The purpose of the study was to get opinions from those most impacted by the issue of racial bias in policing and to propose solutions.
This slideshow considers the privacy and ethical implication when dealing with criminal justice data. The dataset provided by the Bureau of Justice Statistics includes survey data from victims as well as compiles criminal stats. Issues with privacy are highlighted in this slideshare.
3Victimization inthe United StatesAn OverviewCHAPTE.docxtamicawaysmith
3
Victimization in
the United States:
An Overview
CHAPTER OUTLINE
Crime in the Streets: The Big Picture
The Use and Abuse of Statistics
Making Sense of Statistics
The Two Official Sources of Victimization Data
A First Glance at the Big Picture: Estimates of the
Number of New Crime Victims per Year
A Second Glance at the Big Picture: Looking at the
FBI’s Crime Clock
Taking Another Glance at the Big Picture: Looking at
Victimization Rates
Focusing on the Federal Bureau of Investigation’s
Uniform Crime Report
Focusing on the Bureau of Justice Statistics’ National
Crime Victimization Survey (NCVS)
Comparing the UCR and the NCVS
Tapping into the UCR and the NCVS to Fill in the
Details of the Big Picture
Searching for Changes in the Big Picture: Detecting
Trends in Interpersonal Violence and Theft
Taking a Global View: Making International Comparisons
Putting Crime into Perspective: The Chances of Dying
Violently—or From Other Causes
Summary
Key Terms Defined in the Glossary
Questions for Discussion and Debate
Critical Thinking Questions
Suggested Research Projects
LEARNING OBJECTIVES
To find out what information about crime victims is
collected routinely by the federal government’s
Department of Justice.
To become familiar with the ways that victimologists
use this data to estimate how many people were
harmed by criminal activities and what injuries and
losses they suffered.
To become aware of the kinds of information about
victims that can be found in the Federal Bureau of
Investigation’s annual Uniform Crime Report.
continued
58
R
O
D
D
Y
,
A
N
T
H
O
N
Y
I
S
A
A
C
3
7
2
7
B
U
CRIME IN THE STREETS: THE BIG
PICTURE
Victimologists gather and interpret data to answer
questions such as: How many people are harmed by
criminals each year? How rapidly are the ranks of
people who have suffered misfortunes growing?
And, a matter of particular concern, which groups
are targeted the most and the least often? Research-
ers want to find out where and when the majority
of crimes occur, whether predators on the prowl
intimidate and subjugate their prey with their bare
hands or use weapons, and if so, what kinds? Victi-
mologists also want to determine whether indivi-
duals are attacked by complete strangers or people
they know, and how these intended targets act
when confronted by assailants. What proportion
try to escape or fight back, how many are injured,
what percentage need to be hospitalized, and how
much money do they typically lose in an incident?
The answers to basic questions like these, when
taken together, constitute what can be termed the
big picture—an overview of what is really happen-
ing across the United States during the twenty-first
century. The big picture serves as an antidote to
impressions based on direct but limited personal
experiences, as well as self-serving reports circulated
by organizations with vested interests, misleading
media images, crude stereotypes, and widely held
myths. But putting toge ...
Rape in India - A study by Juxt in public interestJuxtConsult
A study to bring forward the real situation of rapes in India. We at Juxt decided to understand public perception and actual reported crime data better.
Reason: We believed that there is lot more which needs to be told to the people of this country…
Rape in India - A study by Juxt in public interest
Police Killings in America
1. Hands up, don't shoot!
A Comprehensive Look at Police Shootings in America
By: Maxwell V. Pederson
2. Introduction and Background
• The fatal police shooting of Michael Brown back in 2014 brought about widespread
outrage and debate across the nation
• The Guardian, a British Newspaper, sought about the reporting of police killings, in
which they found there is no comprehensive database!
• Only as of recently from all the protests and outrage has the FBI decided to create a
voluntary program in which police can choose or choose not to report their justifiable
killings.
• From 2005 - 2012 only 1,110 of the 18,000 police departments reported these justifiable
killings
• Data for this project was gathered from the Guardian's Open Source Police Homicide
database and from FiveThirtyEight’s version of the Guardian data
3. Problem Statement
There has been over 2,100 reported fatalities caused by police since January of
2015. With all the the riots, protests, and uproar caused by certain police shootings
such as Michael Brown, what is the general sentiment about police shootings in
America? Is there reason to believe that police have an inherent bias towards who
they kill? Does the data support the public's sentiment towards police shootings?
Overall Goal: Understand the characteristics of these police shootings to come to a
conclusion on whether the general population’s opinion on police fatalities is
justified by biases police may have towards who they kill.
4. Methods
• Took the FiveThirtyEight data: Started out with 34 attributes and 467 instances
• Only a few attributes consist of the original attributes from the Guardian database (categorical)
• Most attributes are numerical census data added by FiveThirtyEight
• Very unique instances, show the data is fairly linearly-inseparable and may suffer
from the curse of dimensionality
• If columns were used and had bad data/NAs the whole row would be removed
• Most if not all imputation methods will not work well when the data is this linearly-inseparable
with many dimensions
• Extensive use of C5.0 , SVMs , RFs , and BBNs are used in this presentation.
13. Bayesian Belief Network
• Probability that a person is armed
given they are in one of the poorest
districts, given a certain race: 65 ~
69%
• Probability a person was killed by a
gunshot given they were armed:
90% (also the same if not armed)
• Probability a person is armed given
they are a male: 74% and 64% given
they are a female
14. Predictive Modeling Performances
• All of the algorithms have low
accuracy and low sensitivity
• The low sensitivity shows that
the algorithms are
misclassifying unarmed
people as being armed
• Just as in the real world, each
event classification is
extremely different hence the
poor accuracies
15. Conclusion
• The general population of twitter shows a negative sentiment towards police shootings, but it must be
kept in mind the population that is on twitter, young adults. This could serve as an “echo-chamber” effect
as seen in the election.
• Predictive models don't do well on this data because it's too specific and makes the data linearly
inseparable, yet in real life we aren't getting enough of the picture to classify if a person is armed or not.
• The models mostly misclassified people who aren't being armed as being armed, which seems to reflect
controversial killings today.
• Police may or may not have biases, but it can be seen that if these advanced algorithms can’t classify
properly, imagine being the person in the situation when a police call comes in.
• The next steps would be to get a fuller picture on police killings and in general more data. Coupled with
top notch non-biased data scientists, maybe predictive forecasting of crimes could be done.
• As seen a Wall Street Journal however, algorithms aren't biased, the people who work with them are. For
me, I definitely tried to get certain results out of the models, which shows my bias.
16. References
Chen, Eugene. "Map on MapInSeconds.com." MapInSeconds.com by Darkhorse Analytics. Darkhorse
Analytics, 2016. Web. 15 Dec. 2016. <http://mapinseconds.com/>.
McGinty, Jo Craven. "Algorithms Aren't Biased, But the People Who Write Them May Be." The Wall Street
Journal. Dow Jones & Company, 14 Oct. 2016. Web. 15 Dec. 2016. <http://www.wsj.com/articles/algorithms-
arent-biased-but-the-people-who-write-them-may-be-1476466555>.
Swaine, Jon. "About The Counted: Why and How the Guardian Is Counting US Police Killings." The
Guardian. Guardian News and Media, 2015. Web. 15 Dec. 2016. <https://www.theguardian.com/us-news/ng-
interactive/2015/jun/01/about-the-counted>.
Flowers, Andrew. "Fivethirtyeight/data." GitHub. FiveThirtyEight, June 2015. Web. 15 Dec. 2016.
<https://github.com/fivethirtyeight/data/tree/master/police-killings>.
Editor's Notes
Just found 12/15/16: The justice department says it's now trying to use information from the police and open sources such as The Guardian to collectively fill in the gaps!
Link: http://fivethirtyeight.com/features/the-government-finally-has-a-realistic-estimate-of-killings-by-police/
The plot on the left is that of Eric Garner, who was choked out by police and had no weapon on him. It is clear the sentiment is very angry from the wordcloud. The plot on the right is that of Sylville Smith, who did have a weapon on him but dropped it and the policeman fired and killed him. This policeman is currently on trial to see if he will be indicted for the killing. It is clear the sentiment is very negative towards the fact Sylville Smith was killed. What is interesting is that much of the negative sentiment is over the fact that Black Lives Matter groups are fighting Blue Lives Matter groups on twitter.
There is a decent correlation between share_black and median household income. Its apparent though for both however that the dispersion of whether a person is armed or not is fairly random.
These bar graphs show that in general , most people were armed and most people were killed by gunshots. White people make up the majority of people killed, followed by black people.
Although there seems to be a strong correlation on the last slide between poorer counties being predominantly black and richer counties being white according to those who were killed in those counties, this slide is conflicting in those who were armed versus those who were not. Coming up it will be seen that this randomness will hurt the predictive algorithms.
While a randomforest model shows that many census data attributes such as p_income or county_income is the most important, they also are very strongly correlated to each other (after all, some of these features such as comp_income was calculated from dividing h_income by county_income). This is a contradiction as the RF model shows they should remain but the correlation matrix shows some of these features need to be deleted. I chose to delete a few of them so there wouldn't be a correlation, yet the most important ones would still remain as shown in the RF model. Notice raceethnicity is not used often , compare to next slide.
Done over 10 iterations: These are the attributes that are used the most:
Attribute usage:
100.00% age
100.00% raceethnicity
100.00% cause
100.00% county_bucket
100.00% pov
100.00% urate
100.00% college
70.97% share_black
54.52% share_white
33.23% pop
23.87% share_hispanic
A tuned SVM model doesn't do much justice. It somehow made most of the instances support vectors (which defines the classification lines) which can be seen as X's on the left hand graph and boxes around circles on the right hand graph (219 support vectors here). Clearly it's ineffective here. Its supposed to work well on non-linearly separable data and data that has the problem of the curse of dimensionality but it doesn't here. Knncat which similarly should be good on this type of data also didn't work well.
The query model doesn't work very well here. The reason all the percentages are pretty much the same regardless of what is given is because the model doesn't do much better than the data estimates that are already known. For instance being armed and being killed by a gunshot primarily are the primary frequencies and hence have the largest conditional probabilities here.
Wallstreet Journal Article: http://www.wsj.com/articles/algorithms-arent-biased-but-the-people-who-write-them-may-be-1476466555
Its interesting how they tried doing predictive forecasting of crimes and contacted certain people that may commit future crimes even though some of them had never had a criminal history before! It was because of several data points that listed a certain region of the South Side of Chicago of having certain people who may commit crimes in the future.