Applies independent random displacements to each point in a point pattern.
rjitter(X, ...)# S3 method for ppp
rjitter(X, radius, retry=TRUE, giveup = 10000, trim=FALSE,
..., nsim=1, drop=TRUE, adjust=1)
The result of rjitter.ppp is
a point pattern (an object of class "ppp")
or a list of point patterns.
Each point pattern has attributes "radius"
and (if retry=TRUE) "tries".
The function rjitter is generic, with methods for point
patterns (described here) and for some other types of geometrical objects.
Each of the points in the point pattern X is subjected to
an independent random displacement. The displacement vectors are
uniformly distributed in a circle of radius radius.
If a displaced point lies outside the window, then if
retry=FALSE the point will be lost.
However if retry=TRUE, the algorithm will try again: each time a
perturbed point lies outside the window, the algorithm will reject
the perturbed point and
generate another proposed perturbation of the original point,
until one lies inside the window, or until giveup unsuccessful
attempts have been made. In the latter case, any unresolved points
will be included, without any perturbation. The return value will
always be a point pattern with the same number of points as X.
If trim=TRUE, then the displacement radius for each data point
will be constrained to be less than or equal to
the distance from the data point to the window boundary.
This ensures that the randomly displaced points will
always fall inside the window; no displaced points will be lost and no
retrying will be required. However, it implies that a point lying
exactly on the boundary will never be perturbed.
If adjust is given, the jittering radius will be multiplied
by adjust. This allows the user to specify
that the radius should be a multiple of the default radius.
The resulting point pattern
has an attribute "radius" giving the value
of radius used.
If retry=TRUE, the resulting point pattern also has an attribute
"tries" reporting the maximum number of trials needed to
ensure that all jittered points were inside the window.
rexplode
X <- rsyst(owin(), 10, 10)
Y <- rjitter(X, 0.02)
plot(Y)
Z <- rjitter(X)
U <- rjitter(X, 0.025, trim=TRUE)
Run the code above in your browser using DataLab