basic analytical methods | GIS&T Body of Knowledge

Describe the difference between prescriptive and descriptive cartographic models
Develop a flowchart of a cartographic model for a site suitability problem
Discuss the origins of cartographic modeling with reference to the work of Ian McHarg

Relate plots of multidimensional attribute data to geography by equating similarity in data space with proximity in geographical space
Conduct a simple hierarchical cluster analysis to classify area objects into statistically similar regions
Perform multidimensional scaling (MDS) and principal components analysis (PCA) to reduce the number of coordinates, or dimensionality, of a problem
Produce plots in several data dimensions using a data matrix of attributes
Assemble a data matrix of attributes

State the classic formalization of the interaction model
Describe the formulation of the classic gravity model, the unconstrained spatial interaction model, the production constrained spatial interaction model, the attraction constrained spatial interaction model, and the doubly constrained spatial interaction model
Explain how dynamic, chaotic, complex, or unpredictable aspects in some phenomena make spatial interaction models more appropriate than gravity models
Explain the concept of competing destinations, describing how traditional spatial interaction model forms are modified to account for it
Create a matrix that shows spatial interaction
Differentiate between the gravity model and spatial interaction models

Identify several cluster detection techniques and discuss their limitations
Demonstrate the extension of spatial clustering to deal with clustering in space-time using the Know and Mantel tests
Perform a cluster detection analysis to detect “hot spots” in a point pattern
Discuss the characteristics of the various cluster detection techniques

Describe the relationships between kernels and classical spatial interaction approaches, such as surfaces of potential
Outline the likely effects on analysis results of variations in the kernel function used and the bandwidth adopted
Explain why and how density estimation transforms point data into a field representation
Explain why, in some cases, an adaptive bandwidth might be employed
Create density maps from point datasets using kernels and density estimation techniques using standard software
Differentiate between kernel density estimation and spatial interpolation

List the conditions that make point pattern analysis a suitable process
Identify the various ways point patterns may be described
Identify various types of K-function analysis
Describe how Independent Random Process/Chi-Squared Result (IRP/CSR) may be used to make statistical statements about point patterns
Outline measures of pattern based on first and second order properties such as the mean center and standard distance, quadrat counts, nearest neighbor distance, and the more modern G, F, and K functions
Outline the basis of classic critiques of spatial statistical analysis in the context of point pattern analysis
Explain how distance-based methods of point pattern measurement can be derived from a distance matrix
Explain how proximity polygons (e.g., Thiessen polygons) may be used to describe point patterns
Explain how the K function provides a scale-dependent measure of dispersion
Compute measures of overall dispersion and clustering of point datasets using nearest neighbor distance statistics

Describe the implementation of an ordered weighting scheme in a multiple-criteria aggregation
Compare and contrast the terms multi-criteria evaluation, weighted linear combination, and site suitability analysis
Differentiate between contributing factors and constraints in a multi-criteria application
Explain the legacy of multi-criteria evaluation in relation to cartographic modeling
Determine which method to use to combine criteria (e.g., linear, multiplication)
Create initial weights using the analytical hierarchy process (AHP)
Calibrate a linear combination model by adjusting weights using a test data set

Search form