ttestmap: Test of Effect in Locally Fitted Point Process Model

Description

Perform a local \(t\)-test for the presence of a covariate effect in a locally fitted Poisson or Gibbs point process model.

Usage

ttestmap(object, term, ...,
         method = c("exact", "hessian", "taylor"),
         grid = FALSE, 
         ngrid = NULL, grideps = NULL,
         verbose = TRUE)

Value

Object of class "ssf".

Arguments

object: Locally fitted Poisson or Gibbs point process model (object of class "locppm").
term: Term to be dropped from the model. A character string matching a term in the model formula
...: Ignored.
method: Choice of method to be used to evaluate the \(t\) statistic. See Details.
grid: Logical. If FALSE, compute the test statistic at all quadrature points of the model. If TRUE, compute at a coarse grid of locations.
ngrid: Number of grid points (in each axis direction) for the coarse grid. Incompatible with grideps.
grideps: Spacing (horizontal and vertical) between grid points for the coarse grid. Incompatible with ngrid.
verbose: Logical value indicating whether to print progress reports.

Author

Adrian Baddeley Adrian.Baddeley@curtin.edu.au.

Details

The argument object should be a locally-fitted Poisson or Gibbs point process model (object of class "locppm" created by locppm).

This function computes the local \(t\) test statistic for the test that a particular covariate effect in the model is zero. This is described in Baddeley (2016, sections 3 and 5).

References

Baddeley, A. (2017) Local composite likelihood for spatial point patterns. Spatial Statistics, In press. DOI: 10.1016/j.spasta.2017.03.001

Baddeley, A., Rubak, E. and Turner, R. (2015) Spatial Point Patterns: Methodology and Applications with R. Chapman and Hall/CRC Press.

Examples

Run this code

 fit <- with(copper,
        locppm(Points, ~D, covariates=list(D=distfun(Lines)), nd=c(7,15)))
 plot(ttestmap(fit, "D"))

Run the code above in your browser using DataLab