I'm working with animal relocation data. These are x-y coordinates of
radio-collared coyotes over a period of time. Relocations are far enough
apart in time to be considered independent. We want to test if the pattern
of space-use has changed from one year to the next. Relocations roughly
follow a 2D Gaussian distribution, but points are often clustered near one
or more 'cores'. Sample size varies from year to year with a minimum of
n=34. We have applied multi-response permutation procedures (MRPP), but
feel this test is too sensitive to the density of points (vs location). We
have considered using a 2D generalization of the Cramer-von Mises test (to
be adapted from Syrjala, 1996), but this test is sensitive to placement of
the origin and probably requires gridding of the data. Does anybody know
of a good method to compare the spatial distribution of point pattern data?
Cheers,
Alan Swanson
[[alternative HTML version deleted]]
