[R-sig-Geo] Questions of bandwidth in pcf() function

[yaobei]

Dear all，
Currently, I attempted to compare spatial aggregation of species across 
latitude. I plan to use pcf.ppp() function in ‘spatstat’ package. I also 
have a question about the parameter ‘bandwidth’ in pcf function.In 
pcf.ppp() function, the argument bw (bandwidth) is a default value, using 
Epanechnikov kernel with support [−h, h] chosen by the rule of thumb h = 
c/sqrt(λ), bw=h/sqrt(5) is related to lambda which varies with species 
abundance. This may affect the comparison of spatial aggregation of species 
with different abundance.So my question is, should I choose h as a constant 
(e.g., h=30 m, Wiegand, 2007) or use the default method in pcf.ppp() 
function?Best regards, Bei Yao                                      
        [[alternative HTML version deleted]]


_______________________________________________
R-sig-Geo mailing list
R-sig-Geo@r-project.org
https://stat.ethz.ch/mailman/listinfo/r-sig-geo