Plot the Palm intensity diagnostic for a fitted cluster process or Cox process model.
# S3 method for palmdiag
plot(x, ...,
style = c("intervals", "dots", "bands"),
args.dots = list(pch = 16), args.intervals = list(),
xlim=NULL, main)Null.
Object of class "palmdiag" produced by palmdiagnose.
Additional arguments passed to plot.fv
when the fitted curve is plotted.
Character string specifying the style of plot for the nonparametric estimates. See Details.
Arguments passed to points
when style="dots".
Arguments passed to segments
when style="intervals".
Optional range of distances plotted along the horizontal axis. A numeric vector of length 2.
Optional main title for plot.
Adrian Baddeley Adrian.Baddeley@curtin.edu.au.
This function plots the diagnostic proposed by
Tanaka, Ogata and Stoyan (2008, Section 2.3)
for assessing goodness-of-fit of a Neyman-Scott cluster process model
to a point pattern dataset. The diagnostic is computed by
the function palmdiagnose.
First the Palm intensity of the fitted model is plotted as a
function of interpoint distance \(r\) using
plot.fv. Then the nonparametric estimates
of the Palm intensity are plotted on the same graph as follows:
if style="dots", the nonparametric
estimate for each band of distances is plotted as a dot,
with horizontal coordinate at the middle of the band.
This is the style proposed by Tanaka et al (2008).
if style="intervals" (the default), each nonparametric estimate
is plotted as a dot, and a 95% confidence interval is
plotted as a vertical line segment, centred on the dot.
The confidence interval is based on the Poisson approximation.
if style="bands", the nonparametric estimates
are drawn as a continuous curve which is flat on each band of
distances. The 95% confidence intervals are drawn as grey shading.
Tanaka, U., Ogata, Y. and Stoyan, D. (2008) Parameter estimation and model selection for Neyman-Scott Point Processes. Biometrical Journal 50, 1, 43--57.
palmdiagnose
fit <- kppm(redwood)
R <- palmdiagnose(fit)
plot(R, style="d")
plot(R)
plot(R, style="b")
Run the code above in your browser using DataLab