spatstat (version 1.63-2)

fitin.ppm: Extract the Interaction from a Fitted Point Process Model

Description

Given a point process model that has been fitted to point pattern data, this function extracts the interpoint interaction part of the model as a separate object.

Usage

fitin(object)

# S3 method for ppm fitin(object)

# S3 method for profilepl fitin(object)

Arguments

object

A fitted point process model (object of class "ppm" or "profilepl").

Value

An object of class "fii" representing the fitted interpoint interaction. This object can be printed and plotted.

Details

An object of class "ppm" describes a fitted point process model. It contains information about the original data to which the model was fitted, the spatial trend that was fitted, the interpoint interaction that was fitted, and other data. See ppm.object) for details of this class.

The function fitin extracts from this model the information about the fitted interpoint interaction only. The information is organised as an object of class "fii" (fitted interpoint interaction). This object can be printed or plotted.

Users may find this a convenient way to plot the fitted interpoint interaction term, as shown in the Examples.

For a pairwise interaction, the plot of the fitted interaction shows the pair interaction function (the contribution to the probability density from a pair of points as a function of the distance between them). For a higher-order interaction, the plot shows the strongest interaction (the value most different from 1) that could ever arise at the given distance.

The fitted interaction coefficients can also be extracted from this object using coef.

See Also

Methods for handling fitted interactions: methods.fii, reach.fii, as.interact.fii.

Background: ppm, ppm.object.

Examples

Run this code
# NOT RUN {
   # unmarked 
   model <- ppm(swedishpines ~1, PairPiece(seq(3,19,by=4)))
   f <- fitin(model)
   f
   plot(f)

# extract fitted interaction coefficients
   coef(f)

   # multitype
   # fit the stationary multitype Strauss process to `amacrine'
   r <- 0.02 * matrix(c(1,2,2,1), nrow=2,ncol=2)
   model <- ppm(amacrine ~1, MultiStrauss(r))
   f <- fitin(model)
   f
   plot(f)
# }

Run the code above in your browser using DataCamp Workspace