Analyzing Spatial Point Patterns

Abstract

This chapter introduces procedures available in S+SpatialStats for the analysis and modeling of mapped spatial point patterns. A spatial point pattern is a collection of points irregularly located within a bounded region of space. The points can denote locations of naturally occurring phenomena such as earthquakes or plants, or social events such as the locations of small towns or the occurrences of a particular disease. The data set may consist of locations only, or it may be a marked point process, with data values associated with each location (marks). An example of a marked point process is a set of tree locations in a forest, along with their associated diameters at breast height.

In section 3.4 some introductory data explorations were performed on the bramble cane data. In this chapter, a second data set containing mapped locations of maple and hickory trees in a 19.6 acre square plot in Lansing Woods, Clinton County, Michigan, will be used for most analyses [(Diggle, 1983, p. 27), (Gerrard, 1969)]. The data have been scaled so that they reside on the unit square, although this is not necessary for analysis using S+SpatialStats.

In this chapter you will learn to do the following tasks in S+SpatialStats:

• Examine point pattern data for complete spatial randomness (section 6.2).

• Estimate the intensity of a spatial point pattern (section 6.3.1).

• Calculate Ripley’s K-functions (section 6.3.2).

• Simulate a spatial point process (section 6.4).