1. Which societal factors significantly impact gun violence?
2. Which societal factors increase it, and which decrease it?
3. Which societal factor has the strongest correlation with firearm deathrate?
To answer these research questions, we used the datasets provided by the US Cenus Bureau and the US Centers for Disease Control. The Census Bureau provides the annual American Community Survey (ACS), which surveys counties with over 20.000 on various demogrpahic, economic, social, and housing factors. The Centers for Disease Control (CDC) provide, local jurisdiction permitting, annual county mortality counts divided by cause of death; firearm-related is one of the options. With these two datasets we conducted statistical analysis using principal component (factor) analysis, linear regression modelling, and correlations to derive the relation directions and intensities of various ACS factors with the CDC mortality datas. Correlation is a statistical method and measures the strength of a statistical relationship between two variables. The correlation only provides information about the degree of connection between two variables, so a correlation is always undirected, which means that there is no statement about which variable causes the other, so causality is missing. Linear regression is also a statistical method and indicates the relationship between two or more variables. It indicates the relationship between two or more variables. A prerequisite for a regression analysis is that there is a directed linear relationship, which means that there is a dependent and one (or more) independent variables. Our dependent variable is the firearm deathrate. Factor analysis is a method of multivariate statistics in which the data set is modeled by a few factors explaining the relation among variables. Principal component analysis (PCA)is a subcategory of factor analysis with the aim of structuring, simplifying and illustrating extensive data sets by approximating a large number of statistical variables with a smaller number of linear combinations that are as meaningful as possible. The variables are tested for similarities and the types of similarities are summarized as the main varoables, so PCA has a hierarchical approach.