I would like to know if it is possible to create envelopes for combinations of mark correlations with spatstat , generated from markcrosscorr.
In the example on page 645 of the book (2015), I saw that it is possible from the markcorr command, which generates an object of the type fv. However, when I try to do it in a similar way using markcrosscorr, the following message appears: "Error in envelopeEngine(X = X, fun = fun, simul = simrecipe, nsim = nsim, : The function 'fun' must return an object of class 'fv'". Which makes sense, because markcrosscorr generates a fasp (array) object.
Another complementary question is, how to analyze the behavior of marks in cases of inhomogeneous marks patterns? Knowing that the mark correlation function considers that the distribution pattern of marks is homogeneous, would it be incorrect to use it to analyze such marks, since some behaviors could be generated by variations in intensity in certain spatial scales? I'm looking for the smartest way to parse my data marks as there are so many (both categorical and numeric).
Thanks in advance.
Use the command envelopeArray instead of envelope.
Example:
plot(envelopeArray(amacrine, markcrosscorr, nsim=9))