
172 Spatial Point Patterns: Methodology and Applications with R
> D <- density(swp, sigma=bw.diggle, adjust=2)
This is equivalent to selecting the bandwidth by b <- bw.diggle(swp) then computing D <-
density(swp, sigma=2*b).
6.5.1.3 Estimation of intensity at the da ta points
It is sometimes requ ired to estimate the intensity values
λ
(x
i
) at the data points x
i
themselves. For
example, the estimated in tensity values at the data poin ts can be used as weights in some analysis
proced ures. However, the estimates
e
λ
(U)
(x
i
) and
e
λ
(D)
(x
i
) have a large positive bias, because of the
term
κ
(u −x
i
) =
κ
(x
i
−x
i
) =
κ
(0) appearing in the sum in (6.8)–(6.9). To deal with ...