simple_sews: 'simple_sews' objects

In spatialwarnings: Spatial Early Warning Signals of Ecosystem Degradation

simple_sews objects

Description

This help page describes the structure of simple_sews_* objects, such as those defined by the classes simple_sews_single, simple_sews_list

Details

The spatialwarnings uses S3 objects (lists) internally to store indicator values, along with the necessary data to plot and display results. It is not recommended to extract data directly from these objects, as they are subject to change with different releases of the package. The preferred method is to use dedicated generic functions such as plot() or as.data.frame() to display or export the results. Nonetheless, we document the structure of these objects here for reference.

simple_sews objects are returned by all indicator functions that return numeric values. This includes for example generic_sews, flowlength_sews, compute_indicator but *not* patchdistr_sews or spectral_sews, which provide indicators that depend on non-numeric values (e.g. patch-size distribution type), or need to store more information than just a single numerical value (e.g. the spectrum of the input matrix).

simple_sews objects come in multiple variants: simple_sews_single is the result of an indicator function applied to a single matrix, and simple_sews_test_single is the result of indictest applied to a simple_sews_single object. Both these objects have list equivalents, simple_sews_list and simple_sews_test_list which are simply a collection of their 'single' equivalent. These 'list' objects are used to store the results of computations when working with multiple matrices.

A simple_sews_single object is a list with the following components

• value: the indicator values. A vector of length one if there is only one numeric value returned by the indicator function (e.g. flowlength_sews, or with a length above one otherwise

• orig_data: the original matrix on which the indicator was computed

• fun.args: the argument used in the call to the indicator function (the function that given a matrix, returns the spatial metrics of interest)

• taskname: a character string describing the current indicator(s) being computed

• indicf: the indicator function, which given the matrix, returns the spatial metric(s) of interest

simple_sews_test_single have all of the above components, plus the following:

• nulldistr: the null distribution of values, with nulln rows and as many columns as the number of values returned by the indicator function

• null_mean: the mean indicator values in the null distribution

• null_sd: the standard deviation of the null distribution

• null_qsup: the upper quantile of the null distribution, by default the 95 adjust this

• null_qinf: the upper quantile of the null distribution, by default the 05 adjust this

• z_score: the z_score of the observed value relative to the null distribution, i.e. (value - null_mean) / null_sd

• pval: the p-value of the indicator, i.e. the proporation of values of the null distribution that fall below the observed indicator value

• null_method: the method used to produce the null matrices. See indictest for details

• nulln: the number of null matrices used

• get_nullmat: a function that can be called to obtain a randomized matrix

• matrixn: the number of the matrix, can be above one if the computations have been run on a list of matrices, or non-existent if only one matrix was used

See Also

custom_indicator

spatialwarnings documentation built on March 21, 2022, 5:08 p.m.