The function pool
is generic. This is the method for the
class "envelope"
of simulation envelopes. It is used to
combine the simulation data from several simulation envelopes
and to compute an envelope based on the combined data.
Each of the arguments ...
must be an object of class
"envelope"
. These envelopes must be compatible,
in that they are envelopes for the same function,
and were computed using the same options.
In normal use, each envelope object will have been
created by running the command envelope
with the argument savefuns=TRUE
.
This ensures that each object contains the simulated data
(summary function values for the simulated point patterns)
that were used to construct the envelope.
The simulated data are extracted from each object and combined.
A new envelope is computed from the combined set of simulations.
Alternatively, if each envelope object was created
by running envelope
with VARIANCE=TRUE
,
then the saved functions are not required.
The sample means and sample variances from each envelope
will be pooled. A new envelope is computed from the pooled
mean and variance.
Warnings or errors will be issued if the envelope objects ...
appear to be incompatible. Apart from these basic checks,
the code is not smart enough to decide whether it is sensible
to pool the data.
To modify the envelope parameters or the type of envelope that is
computed, first pool the envelope data using pool.envelope
,
then use envelope.envelope
to modify the envelope
parameters.