This topic includes density analysis and cluster analysis.
By summarizing characteristics of spatial distributions, previously hidden patterns may become apparent or evidence of possible patterns investigated.
What can patterns tell me?
Understanding the characteristics of data distributions help you to understand appropriate analysis methods as well as helping to reach reasonable conclusions from your analysis. Spatial patterns deal with both the distributions of values (attributes) and the spatial arrangement of the locations. Summarizing spatial characteristics can, more clearly, show patterns in data.
A continuous surface that shows the intensity of features or values based on sample observations can highlight areas of concentrations. By comparing the intensity of one type of event relative to another (such as a control group), interesting differences can be shown.
Spatial clustering may indicate patterns of underlying processes as similar processes often follow similar locating patterns. Areas of local concentrations of high or low values within a dataset can be identified in data and patterns can be more clearly visualized.
This topic includes a number of case studies that, in part, summarize spatial characteristics of data to better reveal patterns. These are exploratory analyses, designed to demonstrate an approach to a specific problem using ArcGIS. For each case study, additional resources have been made available including workflows that describe how the analysis was done in ArcGIS and a GPK (geoprocessing package) in which all resources (models, scripts, data, layers, and files) needed to perform the described analysis are included in the package.
What questions can I answer?
Understanding patterns and relationships could help you to answer these types of questions:
- What is the density of events?
- Where are the clusters?
- Are the phenomena clustered or dispersed?
- Do the features usually occur in the same places?
- Which areas are at risk?