Residuals for Point Process Model Fitted to Multiple Point Patterns
Given a point process model fitted to multiple point patterns, compute residuals for each pattern.
## S3 method for class 'mppm': residuals(object, type = "raw", ..., fittedvalues = fitted.mppm(object))
- Fitted point process model (object of class
- Type of residuals: either
"inverse". Partially matched.
- Advanced use only. Fitted values of the model to be used in the calculation.
Baddeley et al (2005) defined residuals for the fit of
a point process model to spatial point pattern data.
For an explanation of these residuals, see the help file for
This function computes the residuals
for a point process model fitted to multiple point patterns.
object should be an object of class
The return value is a list.
The number of entries in the list equals the
number of point patterns in the original data. Each entry in the list
has the same format as the output of
That is, each entry in the list is a signed measure (object of
"msr") giving the residual measure for the corresponding
- A list of signed measures (objects of class
"msr") giving the residual measure for each of the original point patterns. See Details.
Baddeley, A., Turner, R., Moller, J. and Hazelton, M. (2005) Residual analysis for spatial point processes. Journal of the Royal Statistical Society, Series B 67, 617--666.
data(waterstriders) fit <- mppm(Bugs ~ x, hyperframe(Bugs=waterstriders)) r <- residuals(fit) # compute total residual for each point pattern rtot <- sapply(r, integral.msr) # standardise the total residuals areas <- sapply(windows.mppm(fit), area.owin) rtot/sqrt(areas)