Takes a Gibbs point process model that has been fitted to several point patterns simultaneously, and produces a list of fitted point process models for the individual point patterns.
subfits(object, what="models", verbose=FALSE)
subfits.old(object, what="models", verbose=FALSE)
subfits.new(object, what="models", verbose=FALSE)An object of class "mppm"
representing a point process model fitted to several point patterns.
What should be returned.
Either "models" to return the fitted models,
or "interactions" to return the fitted interactions only.
Logical flag indicating whether to print progress reports.
A list of point process models (a list of objects of class
"ppm") or a list of fitted interpoint interactions (a list of
objects of class "fii").
object is assumed to have been generated by
mppm. It represents a point process model that has been
fitted to a list of several point patterns, with covariate data.
For each of the individual point pattern
datasets, this function derives the corresponding fitted model
for that dataset only (i.e. a point process model for the object).
If what="models",
the result is a list of point process models (a list of objects of class
"ppm"), one model for each point pattern dataset in the
original fit.
If what="interactions",
the result is a list of fitted interpoint interactions (a list of
objects of class
"fii").
Two different algorithms are provided, as
subfits.old and subfits.new.
Currently subfits is the same as the old algorithm
subfits.old because the newer algorithm is too memory-hungry.
Baddeley, A., Rubak, E. and Turner, R. (2015) Spatial Point Patterns: Methodology and Applications with R. London: Chapman and Hall/CRC Press.
# NOT RUN {
H <- hyperframe(Wat=waterstriders)
fit <- mppm(Wat~x, data=H)
subfits(fit)
H$Wat[[3]] <- rthin(H$Wat[[3]], 0.1)
fit2 <- mppm(Wat~x, data=H, random=~1|id)
subfits(fit2)
# }
Run the code above in your browser using DataLab