[R-sig-Geo] ntamap: mixed anisotropy

[Edzer Pebesma]

Dear Seba, Giannis Spilliopoulos, the author of estimateAnisotropy, sent
me the answer below when I forwarded your email to the intamap-info list
on sourceforge.

Dear Sebastiano and Edzer

Thank for using Intamap package. The "estimateAnisotropy" function is
developed to detect only geometric anisotropy. It is not tested in case
of zonal anisotropy, as  we consider it future work.

As for the anisotropy estimates, given a Cartesian coordinate system
(X,Y) we examine two cases:

a)In the case of zero direction and ratio R (0,R). One should interpret
this result as the correlation length along X axis  is R times bigger
the correlation length along Y axis.

b)In case of  theta degrees and ratio R (theta,R). You should think that
the major correlation length
needs a theta degrees (clockwise) rotation to align with the horizontal
axis. In case of negative angle the rotation should be performed
counter-clockwise. Ratio R in this case yields that the correlation
length on theta degrees is R times bigger than the correlation length in
theta+90 degrees.

To sum up the direction represents the angle between the direction of
the major correlation length and the horizontal axis. While the ratio
represents the ratio of the major to minor correlation lengths.

I hope this helps.

Sincerely
Giannis


seba wrote:
> 
>> Date: Tue, 20 Apr 2010 12:24:34 +0200
>> To: r-sig-geo at stat.math.ethz.ch
>> From: "S. Trevisani" <s.trevisani at irpi.cnr.it>
>> Subject: Intamap: mixed anisotropy
>>
>> Dear list members
>>
>> I'm using some of the functions of the intamap packages.
>> I like very much the estimate anisotropy function, it is really useful
>> for my tasks.
>> But I'm wondering how to deal with zonal or mixed anisotropy
>> considering that
>> the function is designed for detecting geometric anisotropy (anyway, I
>> saw that also in the case of geometric anisotropy, the function tells
>> me correctly the direction of maximum variability, but I'm not sure
>> how to interpret the ratio).
>>
>> Thank you for your feedback!
>>
>> Sincerely
>> Sebastiano
> 
> _______________________________________________
> R-sig-Geo mailing list
> R-sig-Geo at stat.math.ethz.ch
> https://stat.ethz.ch/mailman/listinfo/r-sig-geo

-- 
Edzer Pebesma
Institute for Geoinformatics (ifgi), University of Münster
Weseler Straße 253, 48151 Münster, Germany. Phone: +49 251
8333081, Fax: +49 251 8339763  http://ifgi.uni-muenster.de
http://www.52north.org/geostatistics      e.pebesma at wwu.de