Spatial Statistics
Spatial Data Science
01 Aug 2022
R 6000.00

Brief Description
Spatial data science is a field of data science focusing on spatial data, thereby incorporating both where and why things happen. Spatial analysis started worldwide with the seminal work of Danie Krige, who worked in mining studies at Wits. Its importance to the South African research community is much wider and these days also include poverty alleviation, meteorology and climate, the environment, ecology, agriculture and epidemiology, to name a few. To analyse spatially allows the analyst to incorporate the spatial correlation present in many datasets, without which model interpretation may be incorrect. There is a wealth of knowledge on spatial statistics within South Africa, however, the research field of spatial statistics is still relatively young and much expert guidance is required to build the field in terms of research as well as training. Spatial data science has very important applications in the South African context. There is a need to have trained spatial statisticians as well as spatial data scientists across industry and academia.
Learning Outcomes
After completion of this course, delegates will be able to
  • Analyse spatial data in R as well as theoretically
  • Compute summary spatial functions in R
  • Implement Kriging -Implement Spatial Sampling
  • Implement Spatial Sampling
  • Compare spatial data sets for similarity
Course Content
The course covers the following:
The course covers the following topics and practical examples will be done in R and QGIS:
  • What is Spatial data science
  • The Need for Spatial Analysis
  • Types of Spatial Data
  • Autocorrelation-Concept and Elementary Measures
  • Autocorrelation Functions
  • The Effects of Autocorrelation on Statistical Inference
  • Random, Aggregated, and Regular Patterns
  • Binomial and Poisson Processes
  • Testing for Complete Spatial Randomness
  • Second-Order Properties of Point Patterns
  • The Inhomogeneous Poisson Process
  • Marked and Multivariate Point Patterns
  • Point Process Models
  • Semi-variogram and Co-variogram
  • Covariance and Semi-variogram Models
  • Estimating the Semi-variogram;
  • Spatial Prediction and Kriging: Optimal Prediction in Random Fields
  • Linear Prediction-Simple and Ordinary Kriging
  • Linear Prediction with a Spatially Varying Mean
  • Kriging in Practice
  • Estimating Covariance Parameters
  • Model- and Design-based spatial sampling
  • Testing for similarity of spatial data sets.
Entry Requirements
  • Delegates should have a basic knowledge of R and advanced statistics training
  • Completing the introduction to R provided in the software will be sufficient if R has not been used before.
Course Number:
Catalogue and Category:
Who Should attend:
Statisticians, GIS experts, practitioners and academics and students with basic knowledge of statistics and who would like to develop their spatial statistics skills for research or industry purposes.
Delivery Mode:
Contact Days: