Topics: Point pattern analysis, spatial autocorrelation statistics, and geostatistical interpolation to estimate values across continuous and discrete distributions.
With increasing amounts of spatial data generated each year, spatial analysis is becoming an increasingly useful tool across public health research, ecological modeling, and econometrics. The spatial statistical analysis looks beyond the map to the data mapped and to inquire about the patterns observed. In this tutorial, participants will explore point pattern analysis, spatial autocorrelation statistics, and geostatistical interpolation to estimate values across continuous and discrete distributions.
Objectives:
- Representing geographical data in R
- Finding non-randomness in point maps using spatstat
- Detection and measurement of spatial autocorrelation in lattice data using spdep
- Creating contour-type maps and semivariance using inverse distance weighting and geostatistical methods
Duration: 2 hours
Prerequisites: Basic knowledge of statistics and some previous exposure to working with R is assumed.