latticeDensity (version 1.2.7)

addObservations: Input observations for use in the lattice-based density estimator

Description

This function takes a formLatticeOutput object, which encodes a region possibly with and irregular boundary and holes, and adds point process observations. The observations should be in the form of a matrix or data frame. addObservations is used when the aim is to produce a density map from a point process. If, instead, you wish to produce a nonparametric regression surface given responses and their locations, you should use addQuantVar instead.

Usage

addObservations(formLatticeOutput, observations)

Value

a list with two elements.

init_prob

Numerical vector with the initial probability distribution

which_nodes

vector of nodes to which observations were assigned

Arguments

formLatticeOutput

An object returned by formLattice or editLattice.

observations

A matrix or data frame with two columns.

Author

Ronald P. Barry

Details

Every node in the formLatticOutput object is assigned an initial density that is equal to the fraction of all observations that are nearest to that node. Note that this means observations can be outside the boundary of the region of interest - they will just be associated with the nearest node inside the region. The function returns a vector equal in length to the number of nodes that has the initial density for each node. This vector corresponds to \(p_0\), the inital probability vector as in Barry and McIntyre (2011).

References

Ronald P. Barry, Julie McIntyre. Estimating animal densities and home range in regions with irregular boundaries and holes: A lattice-based alternative to the kernel density estimator. Ecological Modelling 222 (2011) 1666-1672. <doi:10.1016/j.ecolmodel.2011.02.016>

Examples

plot.new()
data(polygon1)
#
nodeFillingOutput <- nodeFilling(poly=polygon1, node_spacing=0.01)
plot(nodeFillingOutput)
formLatticeOutput <- formLattice(nodeFillingOutput)
plot(formLatticeOutput)
#
Pointdata <- splancs::csr(polygon1,30)
Pointdata <- Pointdata[Pointdata[,1]<0.5,]
colnames(Pointdata) <- c("x","y")
plot(polygon1,type="n")
polygon(polygon1)
points(Pointdata,pch=19)
#
densityOut <- createDensity(formLatticeOutput,PointPattern=Pointdata,
                           k=40,intensity=FALSE, sparse = TRUE)
plot(densityOut)