spatstat (version 1.48-0)

methods.rhohat: Methods for Intensity Functions of Spatial Covariate

Description

These are methods for the class "rhohat".

Usage

"print"(x, ...)
"plot"(x, ..., do.rug=TRUE)
"predict"(object, ..., relative=FALSE)
"simulate"(object, nsim=1, ..., drop=TRUE)

Arguments

x,object

An object of class "rhohat" representing a smoothed estimate of the intensity function of a point process.

...

Arguments passed to other methods.

do.rug

Logical value indicating whether to plot the observed values of the covariate as a rug plot along the horizontal axis.

relative

Logical value indicating whether to compute the estimated point process intensity (relative=FALSE) or the relative risk (relative=TRUE) in the case of a relative risk estimate.

nsim

Number of simulations to be generated.

drop

Logical value indicating what to do when nsim=1. If drop=TRUE (the default), a point pattern is returned. If drop=FALSE, a list of length 1 containing a point pattern is returned.

Value

For predict.rhohat the value is a pixel image (object of class "im" or "linim"). For simulate.rhohat the value is a point pattern (object of class "ppp" or "lpp"). For other functions, the value is NULL.

Details

These functions are methods for the generic commands print, plot, predict and simulate for the class "rhohat".

An object of class "rhohat" is an estimate of the intensity of a point process, as a function of a given spatial covariate. See rhohat. The method plot.rhohat displays the estimated function $rho$ using plot.fv, and optionally adds a rug plot of the observed values of the covariate. The method predict.rhohat computes a pixel image of the intensity $rho(Z(u))$ at each spatial location $u$, where $Z$ is the spatial covariate.

The method simulate.rhohat invokes predict.rhohat to determine the predicted intensity, and then simulates a Poisson point process with this intensity.

See Also

rhohat

Examples

  X <-  rpoispp(function(x,y){exp(3+3*x)})
  rho <- rhohat(X, function(x,y){x})
  rho
  plot(rho)
  Y <- predict(rho)
  plot(Y)
  plot(simulate(rho), add=TRUE)
  # 
  fit <- ppm(X, ~x)
  rho <- rhohat(fit, "y")
  opa <- par(mfrow=c(1,2))
  plot(predict(rho))
  plot(predict(rho, relative=TRUE))
  par(opa)