This paper presents statistics on major factors that affects the property crime rates in the U.S.
The property crime rates of 45.7% occurs more in urban areas. About 16.8% of the crimes were committed by high school dropouts and only 0.4% of the crimes that occurs were related to the population density. The type of property crimes that happens includes larceny-theft, home burglary, home invasion, grand theft auto, forgery, and arson. These types of crimes may be caused by factors such as high school dropouts, the population density per square mile, and people living in urban areas. The paper will focus on the crimes against properties such as larceny-theft, home burglary, and grand theft auto, not a person.
Crimes of property happen more often than other crimes. Larceny is a type of theft when someone takes something that does not belong to them. Home burglary is breaking into a private resident with the intent of stealing something. Grand theft auto is an act of stealing a motor vehicle.
Are the property crime rates higher in urban areas? Does the level of education have any effect on the percentage of crimes that are happening? How about the percentage of people living in a population per square mile? All of these factors may play an important role with the number of crimes that are happening today.
Louis J. Moritz, an Operations Manager, collected data from a variety of U.S. government sources. He provided a sample data set of 8 randomly selected factors from 50 states. From those random samples, I used the percentage of dropouts, the size of the population density, and the percentage of residents living in urban areas per state to compare to the percentage of property crimes being committed in the U.S.
Multiple Regression Output:
I identified the individual p-value to test the significance of each of the proposed independent variables •
I used the multiple regression equation of the least squares point estimates of ŷ = b₀ + b₁x₁ + b₂x₂ + b₃x₃ to study more than one independent variables. The intercept of the slope of the line is b₀. o
Y = the percentage of property crimes that occur in the U.S. o
Independent variables: It summarizes the central tendency of the data provided.
x₁ = the percentage of Dropouts in the U.S.
x₂ = the percentage of the population Density in the U.S.
x₃ = the percentage of residents living in an Urban area in the U.S. •
The standard error, also referred to as s, is the idea of the scattered of the actual points around the regression line. •
The adjusted multiple coefficient of determination, also referred to as Adjusted R². •
Inferences to test the hypothesis and confidence intervals, the overall F-test, and the prediction of the dependent variable •
Investigate the multicollinearity by examining if there are correlations among the independent variables that are so high that they may be used as a separate independent variable. Results:
The p-value is basically the area under the left or right tail of a normal curve. I have tested the p-value for each independent variable and compared the value to alpha 0.10. These following p-values (see Exhibit attached) are x₁ p-value = .0005, x₂ p-value = .0006, and x₃ p-value = 2.30E-10. After identifying the p-values from the regression output, I was able to formulate a multiple regression equation of ŷ = -1052.5531 + 57.7544x₁ -1.9318x₂ + 67.8889x₃ from the model. This equation will help explain the relationships between the independent variables of Dropout (x₁), Density (x₂), Urban (x₃) and the dependent variable of Crimes. •
According to the output, the standard error, s, is the point estimate of the standard deviation of the square root of s². The regression analysis shows that s is equal to 745.822. This gives me a rough idea of the actual points that are scattered around the regression line. The less standard error, the more...
Please join StudyMode to read the full document