Describe 1) your sample, 2) the data collection procedure, and 3) a measures section describing your variables and how you managed them to address your own research question.
The sample is from a combination of data sources: US Census (2015), US Crime (2015), and Full-time Law Enforcement Employees in the US (2015). The census data were collected by the US Census Bureau. The crime and law enforcement data were collected by the FBI Uniform Crime Reporting (UCR) Program. The data were joined together on state and county. The sample consists of 2,083 observations, with each observation representing a unique county in the United States. 42 of 50 states (84%) are represented in the data. The states represented in the data, along with the number of counties represented, are as follows:
North Carolina 67
North Dakota 52
New York 48
South Dakota 42
South Carolina 38
West Virginia 29
New Jersey 21
New Mexico 5
New Hampshire 4
Although the American Community Survey (ACS) produces population, demographic and housing unit estimates, it is the Census Bureau’s Population Estimates Program that produces and disseminates the official estimates of the population for the nation, states, counties, cities and towns and estimates of housing units for states and counties. A more detailed overview of the ACS can be found here.
Regarding the crime and law enforcement data, data were collected through the National Incident-Based Reporting System (NIBRS). The data are obtained by means of over 18,000 city, university and college, county, state, tribal, and federal law enforcement agencies voluntarily reporting crime data.
Specifically regarding the crime data:
- The Metropolitan Counties classification encompasses jurisdictions covered by noncity law enforcement agencies located within currently designated Metropolitan Statistical Areas (MSAs). The Nonmetropolitan Counties classification encompasses jurisdictions covered by noncity agencies located outside currently designated MSAs.
- The data used were from all county law enforcement agencies submitting 12 months of complete offense data for 2015.
Specifically regarding the law enforcement data:
- The information in this table is derived from law enforcement employee counts (as of October 31, 2015) submitted by participating agencies.
- The UCR Program defines law enforcement officers as individuals who ordinarily carry a firearm and a badge, have full arrest powers, and are paid from governmental funds set aside specifically to pay sworn law enforcement.
Violent crime rates and property crime rates, as well as crime rates (the combination of violent and property crime rates), were calculated per 100,000 people. The rates of full-time law enforcement employees were also calculated in like manner. These variables were measured in relation to poverty (%), metropolitan/non-metropolitan counties, and region to determine the kinds and strength of associations between such variables.