hotspots.comparison: Hotspots comparison

In AMBarbosa/DeadCanMove: Assess How Spatial Roadkill Patterns Change with Temporal Sampling Scheme

Description

This is a wrapper for most of the functions in this package (one function to rule them all). You'll probably only need to use this one, which in turn calls each of the other functions and does all the calculations in one step.

Usage

hotspots.comparison(dataset, sampl.columns, sampl.intervals, 
region.column, group.column, include.all.together = TRUE, 
confidence = 0.95, min.total.events = 80, min.hotspot.threshold = 2, 
comp.method = "Phi", plot = TRUE, sep.plots = FALSE, 
omit.baseline.interval = TRUE, ...)

Arguments

dataset	name of the matrix or dataframe to analyze
sampl.columns	index numbers of the columns containing the (daily) sampling data, e.g. 4:180
sampl.intervals	intervals at which to extract sampling data, e.g. 1:30; currently must be consecutive and start with 1
region.column	name or index number of the column containing the regions (road segments, sites) to classify as hotspots or non-hotspots
group.column	name or index number of the column containing the taxa or groups to analyse separately, e.g. 3 or "Family"; if NULL, all records will be used together
include.all.together	logical, whether to get subsampling matrices also for the complete data (including all groups combined)
confidence	confidence threshold to consider hotspots (see Malo et al. 2004); defaults to 0.95
min.total.events	minimum total number of events (e.g. deaths) to calculate hotspots for a group
min.hotspot.threshold	minimum number of events for a region to be considered a hotspot
comp.method	the method with which to compare the hotspots obtained with increasing sampl.intervals with those of the baseline scenario; type binary.comp.methods() for available options
plot	logical, whether to plot the correlations between subsamples and baseline for each group (may cause function to fail if sep.plots = FALSE and figure margins are too large for the number of resulting plots)
sep.plots	logical, whether to present the plots in separate windows rather than all in the same window
omit.baseline.interval	logical, whether to omit the first column (correlation of baseline hotspots with themselves) from calculations and results
...	additional arguments to pass to the plot function

Value

A list with 9 elements:

hotspots.list
N.events
HS.threshold
N.hotspots
events.in.HS
event.corrs
event.loss
event.gain
event.balance

Author(s)

A. Marcia Barbosa, J. Tiago Marques, Sara M. Santos

References

Malo, J.E., Suarez, F., Diez, A. (2004) Can we mitigate animal-vehicle accidents using predictive models? J. Appl. Ecol. 41, 701-710 (doi: 10.1111/j.0021-8901.2004.00929.x)

See Also

hotspots

Examples

data(roadkills)

hc <- hotspots.comparison(dataset = roadkills, 
sampl.columns = 4:ncol(roadkills), sampl.intervals = 1:5, 
region.column = "segment", group.column = "taxon",
include.all.together = TRUE, confidence = 0.95, 
min.total.events = 80, min.hotspot.threshold = 2, 
comp.method = "Phi", plot = TRUE, sep.plots = FALSE,
omit.baseline.interval = TRUE, ylim = c(0, 1))

hc

AMBarbosa/DeadCanMove documentation built on Nov. 3, 2021, 10:03 a.m.