Spatial Statistics



The goal of this project was to determine whether the EMS service calls received during the study period were randomly distributed across the study area. The Forth Worth Fire Department has requested assistance to determine if the EMS calls for Battalion 2 have a tendency to cluster. This exercise demostrates four common statistical methods: Average Nearest Neighbor, Getis-Ord General G (High/Low clustering), Multi-Distance Spatial clustering (Ripley's K), and Spatial Autocorrelation or Moran's I Index.


This project was part of the requirements for the Advanced Spatial Analysis (GIS 520) course. The data set representing a single month of EMS calls within the Battalion 2 boundary was provided with the course assignment.


Detailed discussion, strategies, methods used to solve the problem


Spatial statistics is a very valuable tool for the GIS professional. It gives added credibility to any analysis and allows a common means of detecting and quantifying patterns and distributions within the resultant data. The following maps were produced to illustrate the output of each method.