Re: Statistically different distance matrices

On Nov 28, 2:01 am, Tim De Meyer <Tim.DeMe...@xxxxxxxx> wrote:
Hi,

I would like to find a statistical test to solve the following problem. I presume this test already exists, so some pointers to names, websites, software, articles etc. would be very much appreciated.

Suppose one has the geographic locations of 1000 tiny islands in a volcanic region. 10 years later, these geographic locations are measured again, and now the question is: have the islands drifted away from each other or towards each other. This problem comes dome to the question: are the distances in the two corresponding distance matrices statistically different...

Thanks,
Tim

The errors in the locations measurements should be independent from
one island to another. Do you know the standard errors of those
measurements? Are the errors in the coordinates (longitude/latitude,
or whatever) independent? Do you need to take curvature into account?
.