This function needs to be run only once, at the beginning of analysis, to produce a lookup table of spatial autocorrelation (rho) bias correction factors. Since this process takes a long time, due to the need for simulating numerous replicates (generally 50 or more) landscapes at each pair-wise combination of composition and configuration parameterization, we provide a lookup table with the package that is used by the singlemap function internally. Currently, the implementation is limited to 64x64 pixel maps; however, future developments will expand on this limitation and thus the build.lut function is provided for those that may wish to fast-track the construction of scaled lookup tables for analyses of landscapes of different size. Bias corrections are achieved by comparing Whittle estimates of spatial autocorrelation on binary versus continuous surfaces with identical parameterizations.
● Data Source:
CranContrib
● Keywords: distribution
● Alias: build.lut
●
0 images
|
This function produces three separate plots on a 1 row by 3 column output view. The first plot is the expected mean surface for a selected class-focused pattern metric across the possible range of composition and configuration. A dropped marker can be added to the plot that depicts the position of any combination of composition or configuration parameterization. The second and thrid plots provide series of boxplots representing orthogonal cross-sections of the surface in the first plot, intersecting at the specified location. This provides a sense of how the selected metric's expected value and variability will change as the composition and/or configuration parameter are altered.
● Data Source:
CranContrib
● Keywords: distributions
● Alias: surfplot
●
2 images
|
A simple drawing function for matrices that are actually representing raster landcape maps. This function also controls the use of colour for nominal maps. This is a generic function for drawing any raster image that should not be drawn as a matrix (where the origin is not at the lower-left corner, but rather the upper-left corner. This function draws a matrix as a map using the proper positioning of the origin and gridded values.
● Data Source:
CranContrib
● Keywords: hplot
● Alias: imaks
●
1 images
|
|
This function estimates the composition and configuration parameters for a binary map having 64x64 pixel extent. The 64x64 extent is a current limitation and will be expanded upon in subsequent updates. The parameter estimates are corrected for bias introduced by the Whittle estimation and then these parameters are used to simulate a series of statistically similar landscapes. Each of these simulated landscapes are processed with SDMTools to compute class-focused pattern metrics that are saved to produce empirical (null) distributions for each metric, given the specified level of spatial autocorrelation (configuration) and class proportion (composition). The results can be saved to a new object that is later used for producing graphical and statistical outputs.
● Data Source:
CranContrib
● Keywords: classes, distribution
● Alias: singlemap
●
0 images
|
This function iteratively cycles through combinations of 9 binary proportion intervals and 11 spatial autocorrelation intervals and at each simulates a specified number of statistically similar binary landscape patterns. Each landscape is processed by SDMTools to produce empirical (null) distributions for class-focused pattern metrics. These surfaces can then be plotted or assessed for their mean values at any point (along with their variability).
● Data Source:
CranContrib
● Keywords: distribution
● Alias: buildsurfs
●
2 images
|
|
This package permits the estimation of composition and configuration parameters from a binary landscape map (provided as a numeric matrix). These values are then used to simulate a series of statistically similar maps from which a suite of class-focused pattern metrics are computed and stored to produce empirical (null) distributions for each pattern metric. The package also produces probabilities and allows the testing of whether metric values measured for a map could have been produced by random chance. Numerous graphic outputs are also produced to facilitate the analysis and comparison of spatial patterns at the class-focus.
● Data Source:
CranContrib
● Keywords: package
● Alias: PatternClass, PatternClass-package
●
0 images
|
|
This function produces boxplots comparing the expected values (empirical, null distributions) for a given class-focused pattern metric between two maps.
● Data Source:
CranContrib
● Keywords: distribution
● Alias: doubleplotter
●
0 images
|
A CAR landscape simulator for isotropic conditions.
● Data Source:
CranContrib
● Keywords: hplot
● Alias: CARsimu
●
1 images
|
|
Produce a series of one or more boxplots depicting the empirical (null) distribuitons of class-focused pattern metrics, as computed for a single landscape map.
● Data Source:
CranContrib
● Keywords: distributions
● Alias: singleplotter
●
0 images
|
providing 
.