spherstat-package: Analysis of Point Patterns on a Sphere

In baddstats/spherstat: Spatial Point Pattern Analysis, Geometry and Trigonometry for the Sphere

Analysis of Point Patterns on a Sphere

Description

A package for analysing spatial point pattern data on the sphere, or observed in a region of the sphere.

Details

This package allows a user to analyse point pattern data on a sphere, or a subset of a sphere. Subsets of the sphere that are currently supported are the spherical cap, band, wedge, and polygon. Currently this package supports:

• calculations in spherical geometry and trigonometry;

• calculation of pairwise and nearest neighbour distances between points;

• calculation of distance from point to boundary of window;

• estimation of summary functions including the spherical analogues of Ripley's K function, the nearest neighbour distance distribution function G, the empty space function F and the J function;

• simulation of Poisson, Matern inhibition, Strauss, Hard-core and Neyman-Scott point processes;

• model-fitting for Poisson point processes and Neyman-Scott processes.

The preferred coordinate system for data given to functions in this package is the spherical coordinate system. In other words, the coordinate of a point should be given as (theta, phi), where theta is the colatitude, between 0 and pi, and phi is longitude and is between 0 and 2 * pi. The north pole has colatitude 0 and arbitrary longitude (although for most cases, use phi=0), and longitudes are measured in anticlockwise direction. Some functions allow data to be given using Cartesian coordinates (x,y,z).

Note

Many functions in these package are the analogues for point processes on the sphere of functions available in the package spatstat for point processes in R^2 or R^3. Elements of the code and help pages in this package have been taken with permission from corresponding material in spatstat.

Author(s)

Tom Lawrence <email: [e-mail]> Adrian Baddeley

Examples

  sph <- sphwin(type="sphere")
  sph.pp <- rpoispp.sphwin(win=sph, lambda=10)
  sph.Gest <- Gsphere(X=sph.pp, win=sph)

baddstats/spherstat documentation built on Feb. 6, 2023, 1:45 a.m.