Request: Spatial Cross Correlation

[yousef2233]

Hello Friends.

Anyone knows how to calculate: Spatial Cross-Correlation or Multivariate Auto-correlation ? One thing I found is Geoda, but I checked it with some data of my own; the results are not correct I think !!

Regards,

[EmperoR]

since this topic ask bout method and how to thingy, then discussion is the right place, enjoy

[Lurker]

Some of those function found in R Statistical software

[hide]

http://www.r-project.org/

[/hide]

[hide]

https://stat.ethz.ch/pipermail/r-help/2008-April/158519.html

[/hide]

and

[hide]

http://pbil.univ-lyon1.fr/ADE-4/ade4-html/multispati.randtest.html

[/hide]

hem, I dont know much bout this software  :lipsrsealed:

[yousef2233]

Thank you for you search Lurker,  :grin:

I had found this soft either, but seems a little strange for me to extract what I want 

by the way, R has some toolboxes for Arcgis, R Tools; consists of Logit Regression and Point Clustering.

Regards,

[Lurker]

I found plugin for matlab

check here :

[hide]

http://www.spatial-statistics.com/software_index.htm

[/hide]

but you need matlab  :cry:

[yousef2233]

hi friends,

here is the the code for spatial cross-correlation (Matlab)

there are 2 surfaces we are going to compare or find correlations

maybe you should convert them to raster first

A = imread ('...'/firstraster.jpg');

B = imread ('.../secondraster.jpg');

Result = normxcorr2(B,A);

size if B should be equal or lesser than size of A

the result is an arrey of correlation as kernel ( B moves across the Image A )

max(max(Result)) % the max xross corr found by kernel

imshow (Result) % xross surface