Crime statistical Analysis

Crime statistical Analysis

Introduction

Crimes have always been the major concern for the US society. Many studies have been done on crimes to gather information of different factors that are responsible for the increase in the crimes. People always appreciates a society without crimes but it should be considered that there are some major factors which affects the society and have immense relationships with increasing rate of crimes in the society. In this study, a data set of 50 states of US has been gathered and almost 8 different crime factors have been noticed and their data is also available. The factors which we think are responsible for increasing crimes are PINCOME (Per capita income of each state), DROPOUT (High school droop out rate %), PRECIP (Average participation in inches in the major city in each state), PUBAID (Percentage of public aid recipients), DENSITY (Population total miles), KIDS (Public aid for families with children), UNEMPLOY (Percentage of unemployed workers), URBAN (Percentage of the residents living in the urban areas). The Numeric data for crime is taken as property crimes per hundred thousand inhabitants in US (property crimes include burglary, larceny, theft and motor vehicle thefts).

The factors above are considered as having major contribution in increasing crimes, so a statistical study will be applied on the crime rate to find out whether the factors/variables which we have taken are certainly related or not. Further, some statistical tools will also be used to gather complete information about the study organized. It is hoped that this study is going to give some fruitful results in future to control the crime rate in US.

Data Analysis for Increasing Crimes

The data for this assignment has been retrieved from a variety of US official sources, including the 1988 uniform crime reports, federal bureau of investigation, the office of research and statistics, Us department of education etc. In fact all the departments from where the data is retrieved are all responsible departments and their source of information can never be denied. The linear regression model of this case can be modeled as

Following, the analysis is being done on the given data:

Descriptive Statistics for crime rates

Mean

Std. Deviation

N

CRIMES

4.5592E3

1231.94221

50

PINCOME

1.5442E4

2778.40070

50

DROPOUT

24.0760

7.03970

50

PUBAID

5.3900

1.89965

50

DENSITY

1.6392E2

231.18137

50

KIDS

3.2738E2

120.00134

50

PRECIP

34.7620

14.30354

50

UNEMPLOY

5.4880

1.90912

50

URBAN

66.8440

14.56695

50

Analysis of Descriptive statistics and correlations

The above data shows the mean and standard deviations of the crimes and other depending factors with a total size of 50 samples. The standard deviations of the above variables are appropriate according to the given data with no outliers. Below the correlation of coefficients has been calculated and concluding how much of each every variable is dependent on the other. For e.g. PINCME (per capita income) is .279 i.e. is explaining 27.9% of the increasing crime rate. Similarly, all the variables are somewhat correlated to one another. The level of significance shows that the resulting coefficients are significant or not, for e.g. significance level PINCME (per capita income) is .025 showing that this variable can be rejected at even 2.5% (Sherri L. Jackson, 2011).

Correlations

CRIMES

PINCOME

DROPOUT

PUBAID

DENSITY

KIDS

PRECIP

UNEMPLOY

URBAN

Pearson Correlation

CRIMES

1.000

.279

.410

-.096

.061

.075

-.080

.055

.676

PINCOME

.279

1.000

-.021

-.137

.630

.645

.093

-.478

.572

DROPOUT

.410

-.021

1.000

.415

.107

-.350

.517

.381

.148

PUBAID

-.096

-.137

.415

1.000

.145

-.037

.438

.411

-.052

DENSITY

.061

.630

.107

.145

1.000

.307

.297

-.395

.484

KIDS

.075

.645

-.350

-.037

.307

1.000

-.201

-.402

.315

PRECIP

-.080

.093

.517

.438

.297

-.201

1.000

.130

-.154

UNEMPLOY

.055

-.478

.381

.411

-.395

-.402

.130

1.000

-.137

URBAN

.676

.572

.148

-.052

.484

.315

-.154

-.137

1.000

Sig. (1-tailed)

CRIMES

.

.025

.002

.254

.337

.302

.290

.352

.000

PINCOME

.025

.

.441

.172

.000

.000

.260

.000

.000

DROPOUT

.002

.441

.

.001

.230

.006

.000

.003

.153

PUBAID

.254

.172

.001

.

.158

.400

.001

.002

.361

DENSITY

.337

.000

.230

.158

.

.015

.018

.002

.000

KIDS

.302

.000

.006

.400

.015

.

.081

.002

.013

PRECIP

.290

.260

.000

.001

.018

.081

.

.185

.144

UNEMPLOY

.352

.000

.003

.002

.002

.002

.185

.

.172

URBAN

.000

.000

.153

.361

.000

.013

.144

.172

.



Coefficients

Model

Unstandardized Coefficients

Standardized Coefficients

t

Sig.

95% Confidence Interval for B

Collinearity ...