Module 1 - Crime Analysis

 Module 1- Crime Analysis, introduces us to selected techniques in crime analysis, aggregate crime events to determine crime rates, examine spatial patterns in crime rates, and compare the reliability of crime hotspot mapping for crime prediction.

Analysis steps for Grid Overlay:

The spatial join between the grid cells and the 2017 homicide Washington D.C. feature layers created a grid that included the homicide count.

The Select by Attributes on the grid feature layer of all grids with a homicide count greater than zero yielded a new feature layer that ultimately led to creating the top 20 percent using quintile classification.

Analysis steps for Kernel Density:

Using the Kernel Density tool, and the values from the lab instructions, yielded results that indicated the mean as well as the maximum value.  The requirement was to use two breaks for classification, one break three (3) times the mean, and the other break is the maximum value.

Then using the Reclassify tool to use these values to reclassify the raster, then use the Raster to Polygon tool to create a polygon feature class.

The Select by Attributes on the newly creature feature class requirement is to select only the value of 2, all the polygons above 3 times the mean.

Analysis steps for Local Moran's I:

The spatial join between census tracts and 2017 Washington D.C. homicides creates a new join-count field.

Then add a new field for the crime rate and using the field calculator to determine the number of homicides per 1000 housing units.

Using the Cluster and Outlier Analysis (Anselin Local Moran's I) Spatial Statistics tool to yield classification clusters.

Use a SQL query to select the high-high clusters, which are stored in the COType IDW field.

Once the high-high clusters are selected, use the Dissolve tool to create one polygon feature class.