
364 Spatial Point Patterns: Methodology and Applications with R
The arguments xincin,yincin are the coord inates of the incinerator. By specifying default values
for them, we do not have to handle these values again. Next we define the raised incidence term
b
θ
(u):
> raisin <- function(x,y, alpha, beta) {
1 + alpha * exp( - beta * d2incin(x,y))
}
We the n fit the model using ippm (this can be slow):
> chorleyDfit <- ippm(Q
~
offset(log(smo) + log(raisin)),
start=list(alpha=5, beta=1))
The argument start lists the irregular parameters over which the likelihood is to be maximised,
and gives their starting values for the iterative algorithm. The parameter names ...