A tool for exploratory statistical analysis on land use data
A prerequisite to the development of realistic models of land use change is the identification of the most important drivers of change.
This tool gives investigators the possibility to summarize the knowledge about interdependent spatial processes in the GIS lattice.
This summary can help to draw substantive conclusions about the region under study.A tool
About the Statistical analysis for spatial land use data tool
This software provides a means to perform exploratory statistical analysis for the non-temporal spatial data.
The goal is to deduce conditions associated with the level of the response in different areas of the studied region.
The data should be compiled for the census areas, defined by the regional administrative division. Additionally, the tool allows estimating accuracy of the approximation by a statistical model to the higher resolution data, defined on the GIS lattice.
Software is supplied in several packages (below).
- Introduction to Exploratory Spatial Analysis
- Permutation Hypothesis Testing and Bootstrapping
- Testing Spatial Autocorrelation with the Bootstrap
How the tool works
The regional data is summarized by a multiple regression model with the unknown joint distribution of error terms.
Hypothesis testing for model evaluation is done by the permutations method.
Confidence intervals for regression estimates are constructed using bootstrapping approach.
Accuracy of model approximation to the GIS lattice is assessed in every cell and summarized by statistics from the derived sample of accuracy values.
Additionally, approximation accuracy can be estimated for a cluster of cells in the GIS lattice.
This work received support from the EU FP7 project COMPLEX (grant no. 308601).