| plot.influence.ppm {spatstat.model} | R Documentation |
Plot Influence Measure
Description
Plots an influence measure that has been
computed by influence.ppm.
Usage
## S3 method for class 'influence.ppm'
plot(x, ..., multiplot=TRUE)
Arguments
x |
Influence measure (object of class |
... |
Arguments passed to |
multiplot |
Logical value indicating whether it is permissible to plot more than one panel. This happens if the original point process model is multitype. |
Details
This is the plot method for objects of class "influence.ppm".
These objects are computed by the command influence.ppm.
For a point process model fitted by maximum likelihood or
maximum pseudolikelihood (the default), influence values are
associated with the data points.
The display shows circles centred at the data points
with radii proportional to the influence values.
If the original data were a multitype point pattern, then
if multiplot=TRUE (the default),
there is one such display for each possible type of point,
while if multiplot=FALSE there is a single plot
combining all data points regardless of type.
For a model fitted by logistic composite likelihood
(method="logi" in ppm) influence values
are associated with the data points and also with the
dummy points used to fit the model. The display consist of two
panels, for the data points and dummy points respectively,
showing circles with radii proportional to the influence values.
If the original data were a multitype point pattern, then
if multiplot=TRUE (the default),
there is one pair of panels for each possible type of point,
while if multiplot=FALSE there is a single plot
combining all data and dummy points regardless of type.
Use the argument clipwin to restrict the plot to a subset
of the full data.
Value
None.
Author(s)
Adrian Baddeley Adrian.Baddeley@curtin.edu.au, Rolf Turner rolfturner@posteo.net and Ege Rubak rubak@math.aau.dk.
References
Baddeley, A. and Chang, Y.M. and Song, Y. (2013) Leverage and influence diagnostics for spatial point process models. Scandinavian Journal of Statistics 40, 86–104.
See Also
Examples
X <- rpoispp(function(x,y) { exp(3+3*x) })
fit <- ppm(X, ~x+y)
plot(influence(fit))